# AI Chess Leaderboard (dubesor.de): plain-text data snapshot Auto-generated from the same data as the interactive page: https://dubesor.de/chess/chess-leaderboard Last updated: 2026-11-02 02:05 CET Coverage: 361 AI models, 5,200 chess matches, 21,520 puzzle challenges. Methodology and context: see the page above. Elo is relative to this LLM pool only; each mode has separate Elo. "˟" = deprecated model. "random-mover" = random-move baseline. "maia5-1500" = human-like neural net reference (not an LLM). Human games excluded. Columns: Cost = avg $ per game (~ = bill-reconstructed) | Acc = Stockfish game accuracy | Blunder = % moves losing 15%+ win prob. | WR = (W + D/2)/games | Mat = avg material diff at end | Turns = avg full moves | Tok = output tokens/move | Spd = avg time/move | Legal = % legal attempts (Mixed: Reasoning / Continuation) ## Detailed Player Statistics: 5+ games, Mixed Modes (306 models) | # | Model | Elo | Cost | Games | W-D-L | Acc | Blunder | WR | Mat | Turns | Tok | Spd | Legal | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | gemini-3.1-pro-preview | 1856 ±84 | $1.72 | 82 | 62-7-13 | 90% | 2.3% | 79.9% | +7.3 | 42.1 | 3320 | 34s | 100% / 99.6% | | 2 | gemini-3-pro-preview ˟ | 1834 ±100 | ~$1.65 | 75 | 64-7-4 | 90.7% | 2.2% | 90% | +12.1 | 40.2 | 3319 | 40s | 100% / 98.7% | | 3 | gemini-3.8-flash | 1809 ±105 | $0.19 | 39 | 28-5-6 | 91.3% | 1.9% | 78.2% | +8.4 | 45.1 | 1005 | 10s | 99.9% / 99.4% | | 4 | gemini-3.7-flash ˟ | 1807 ±111 | $0.07 | 38 | 28-5-5 | 89.8% | 2.4% | 80.3% | +9.1 | 42.9 | 599 | 5.1s | 100% / 99.5% | | 5 | gemini-3.6-flash | 1750 ±103 | $0.35 | 47 | 29-6-12 | 88.7% | 2.6% | 68.1% | +5.4 | 43.6 | 1186 | 7.4s | 100% / 99.2% | | 6 | gemini-3.5-flash ˟ | 1715 ±84 | $0.69 | 63 | 40-12-11 | 88.5% | 2.7% | 73% | +6.5 | 45.5 | 1558 | 9.0s | 100% / 93.5% | | 7 | gpt-6-astra | 1640 ±84 | $0.87 | 47 | 24-10-13 | 84.5% | 3.4% | 61.7% | +0.2 | 48.2 | 496 | 11s | 100% / 98.9% | | 8 | gemini-4-argon | 1630 ±98 | $0.18 | 35 | 20-4-11 | 84.8% | 3.2% | 62.9% | +3.8 | 46.7 | 277 | 5.8s | 100% / 98.6% | | 9 | gpt-5.1-codex ˟ | 1611 ±98 | ~$6.59 | 37 | 18-8-11 | 87.9% | 3.5% | 59.5% | +0.2 | 45.6 | 13969 | 194s | 100% / 93.3% | | 10 | gpt-5-codex ˟ | 1602 ±139 | ~$9.84 | 36 | 27-3-6 | 84.8% | 3.1% | 79.2% | +8.8 | 42.6 | 22596 | 324s | 100% / 92.7% | | 11 | gemini-3-flash-preview | 1583 ±69 | $0.03 | 105 | 61-26-18 | 86.3% | 3.1% | 70.5% | +6.2 | 43.1 | 145 | 2.6s | 99.9% / 99.7% | | 12 | claude-opus-5.5 | 1570 ±94 | $0.70 | 38 | 16-6-16 | 85.3% | 2.8% | 50% | +0.4 | 51.4 | 515 | 8.1s | 100% / 98.3% | | 13 | gpt-5.5 | 1568 ±88 | $4.02 | 53 | 22-9-22 | 84% | 4.4% | 50% | +3.2 | 43.1 | 3023 | 57s | 100% / 95.6% | | 14 | maia5-1500 | 1548 ±86 | - | 48 | 24-7-17 | 83.7% | 3.2% | 57.3% | +5.4 | 38.1 | - | - | 100% / 100% | | 15 | gpt-5 | 1514 ±93 | $3.80 | 54 | 33-6-15 | 82.8% | 4.3% | 66.7% | +4.5 | 40.7 | 9244 | 159s | 100% / 97.8% | | 16 | o3 | 1496 ±79 | $2.72 | 71 | 36-15-20 | 81.4% | 4.1% | 61.3% | +3.3 | 46.6 | 6939 | 91s | 100% / 89.7% | | 17 | gpt-6.1-sol | 1493 ±92 | $0.18 | 39 | 16-7-16 | 84.7% | 3.2% | 50% | -1.2 | 53.5 | 512 | 14s | 100% / 98.6% | | 18 | gpt-6.1-terra | 1490 ±99 | $0.10 | 35 | 21-5-9 | 82.7% | 4.5% | 67.1% | +5.3 | 44.9 | 661 | 7.2s | 99.9% / 99.4% | | 19 | claude-fable-5 | 1465 ±88 | $3.60 | 62 | 33-7-22 | 78.5% | 5.5% | 58.9% | +3.3 | 43.7 | 1436 | 23s | 99.9% / 94.5% | | 20 | gpt-5.6-sol | 1459 ±70 | $1.80 | 68 | 29-20-19 | 79.6% | 5.2% | 57.4% | +1.7 | 46.4 | 1398 | 29s | 100% / 90.4% | | 21 | gpt-4.5-preview ˟ | 1454 ±155 | ~$2.18 | 35 | 25-8-2 | 82.1% | 4.3% | 82.9% | +8.8 | 43.1 | 133 | 3.4s | 100% / 98.7% | | 22 | deepseek-v4-flash-0731 | 1444 ±97 | $0.40 | 46 | 27-3-16 | 81.4% | 5.3% | 62% | +4 | 45.5 | 31294 | 332s | 100% / 89.5% | | 23 | kimi-k3 | 1444 ±103 | ~$7.22 | 37 | 22-5-10 | 81.1% | 4.1% | 66.2% | +4.2 | 43.1 | 10897 | 340s | 99.9% / 97.2% | | 24 | gpt-5.1 | 1442 ±101 | $2.16 | 39 | 20-4-15 | 83.5% | 4.3% | 56.4% | +1.4 | 40.9 | 4933 | 96s | 100% / 88.2% | | 25 | deepseek-v4-pro-0813 | 1432 ±119 | $3.42 | 26 | 15-1-10 | 79.3% | 5% | 59.6% | +5.3 | 49.1 | 32609 | 441s | 100% / 97.7% | | 26 | qwen3.8-max | 1430 ±101 | ~$7.75 | 36 | 20-5-11 | 79.1% | 4.6% | 62.5% | +4.3 | 48.4 | 26344 | 484s | 100% / 98.7% | | 27 | grok-4 ˟ | 1415 ±118 | ~$13.03 | 40 | 15-9-16 | 81.7% | 4.4% | 48.8% | +5.2 | 40.2 | 21227 | 596s | 100% / 94.3% | | 28 | gemini-3.1-flash-lite-preview | 1403 ±78 | $0.008 | 84 | 44-17-23 | 78.1% | 5.2% | 62.5% | +3.4 | 42.2 | 164 | 1.8s | 98.9% / 94% | | 29 | grok-4.20-reasoning | 1362 ±89 | $1.00 | 47 | 18-13-16 | 78.1% | 5.6% | 52.1% | +3.1 | 44.1 | 3423 | 24s | 100% / 81% | | 30 | deepseek-v4.1-flash-1017 | 1359 ±104 | $0.62 | 28 | 12-3-13 | 80.6% | 5.3% | 48.2% | +0.3 | 43.6 | 23080 | 117s | 100% / 97.3% | | 31 | gpt-5.1-codex-max ˟ | 1354 ±93 | ~$3.58 | 34 | 9-10-15 | 80.8% | 5.3% | 41.2% | -3 | 43.1 | 7920 | 103s | 100% / 90.9% | | 32 | deepseek-v4.1-flash | 1353 ±104 | $0.85 | 31 | 15-2-14 | 79.5% | 4.3% | 51.6% | -0.1 | 45.2 | 27971 | 132s | 100% / 98.2% | | 33 | gpt-3.5-turbo-instruct ˟ | 1343 ±74 | $0.04 | 125 | 80-14-31 | 74.1% | 9.2% | 69.6% | +3.7 | 34 | 224 | 2.0s | 87.6% / 91.5% | | 34 | gemini-3.5-flash-lite | 1342 ±85 | $0.03 | 50 | 16-10-24 | 76.6% | 5.4% | 42% | -0.9 | 51.4 | 141 | 1.8s | 98.4% / 94.6% | | 35 | hy3 | 1337 ±86 | $0.18 | 43 | 20-14-9 | 78.3% | 7.2% | 62.8% | +5.8 | 42 | 7366 | 113s | 100% / 93.2% | | 36 | gpt-6-sol | 1321 ±86 | $0.51 | 37 | 12-13-12 | 77.3% | 5.2% | 50% | +1.6 | 51.9 | 991 | 16s | 100% / 95.9% | | 37 | claude-fable-5.1 | 1305 ±99 | $3.54 | 30 | 10-7-13 | 77.1% | 4.8% | 45% | +0.8 | 52.9 | 1115 | 19s | 100% / 93.2% | | 38 | minimax-m3.1-flash | 1301 ±111 | $0.48 | 26 | 17-0-9 | 78% | 6.2% | 65.4% | +1.8 | 38 | 23784 | 250s | 100% / 82.6% | | 39 | claude-sonnet-5.5 | 1292 ±104 | $0.43 | 34 | 18-1-15 | 79.7% | 4.2% | 54.4% | +1.6 | 44.8 | 743 | 7.8s | 99.9% / 89.7% | | 40 | gpt-5.6-luna | 1250 ±81 | $0.35 | 50 | 15-13-22 | 77.8% | 6.5% | 43% | -3.3 | 44.3 | 1471 | 15s | 100% / 83% | | 41 | gpt-5.2-codex ˟ | 1245 ±96 | ~$1.46 | 37 | 10-10-17 | 75.7% | 5.6% | 40.5% | -2.8 | 41.1 | 2456 | 38s | 100% / 86.1% | | 42 | gpt-3.5-turbo ˟ | 1240 ±80 | $0.02 | 90 | 52-22-16 | 75.8% | 9.3% | 70% | +4.6 | 37.5 | 150 | 1.9s | 89.6% / 92.8% | | 43 | glm-5.3-flash | 1222 ±119 | $0.48 | 23 | 9-2-12 | 80.3% | 5.4% | 43.5% | -2.6 | 43.2 | 30324 | 434s | 99.9% / 85.8% | | 44 | gpt-5.6-terra | 1209 ±77 | $0.66 | 51 | 11-18-22 | 72.7% | 6.1% | 39.2% | +0.7 | 47.2 | 975 | 14s | 99.9% / 82.2% | | 45 | chatgpt-4o-latest ˟ | 1203 ±90 | ~$0.25 | 35 | 11-15-9 | 71.8% | 7.9% | 52.9% | +1.4 | 48.5 | 164 | 1.6s | 99.4% / 95.3% | | 46 | gpt-5.3-codex | 1184 ±93 | ~$1.01 | 32 | 9-11-12 | 75.9% | 6.1% | 45.3% | +0.3 | 39.3 | 1668 | 32s | 100% / 86.7% | | 47 | gpt-5-chat ˟ | 1184 ±77 | ~$0.10 | 66 | 28-20-18 | 73.6% | 6.8% | 57.6% | +1.3 | 45.4 | 163 | 2.4s | 99.8% / 91.4% | | 48 | gpt-4o | 1179 ±66 | $0.13 | 89 | 39-31-19 | 73.9% | 7.8% | 61.2% | +2.5 | 45.5 | 150 | 2.6s | 99.7% / 95.8% | | 49 | grok-build-0.1 | 1167 ±85 | $0.86 | 39 | 15-16-8 | 73.4% | 6.9% | 59% | +10.4 | 41.8 | 9261 | 69s | 100% / 80.9% | | 50 | kimi-k2.6 | 1162 ±98 | ~$2.80 | 41 | 21-7-13 | 68.5% | 8.9% | 59.8% | +3.1 | 37.5 | 18353 | 325s | 100% / 90% | | 51 | claude-sonnet-5 | 1158 ±79 | $1.69 | 45 | 16-16-13 | 73.3% | 7.1% | 53.3% | -0.3 | 45.5 | 3296 | 40s | 99.9% / 85.4% | | 52 | muse-spark-1.3 | 1147 ±104 | $1.54 | 25 | 12-5-8 | 73.4% | 6.3% | 58% | +4.3 | 49.9 | 6913 | 76s | 100% / 93.2% | | 53 | grok-4.3 | 1145 ±102 | $0.44 | 41 | 11-12-18 | 71.4% | 9.7% | 41.5% | -2.4 | 42.5 | 3472 | 44s | 100% / 78.7% | | 54 | qwen3.8-27b | 1142 ±138 | $3.32 | 11 | 5-2-4 | 75.1% | 5.6% | 54.5% | +1.9 | 48.8 | 27197 | 337s | 99.8% / 87.3% | | 55 | grok-4.5 | 1135 ±92 | $0.96 | 40 | 14-13-13 | 67.1% | 8.7% | 51.3% | -2.4 | 45.3 | 3150 | 40s | 100% / 86.6% | | 56 | gpt-5.2 | 1127 ±94 | ~$2.49 | 39 | 11-11-17 | 73.5% | 5.8% | 42.3% | -1.2 | 45.8 | 3540 | 75s | 100% / 80.6% | | 57 | qwen3.8-flash | 1110 ±111 | $0.82 | 23 | 10-4-9 | 72% | 7.4% | 52.2% | +2.9 | 42.9 | 39209 | 380s | 99.6% / 94.1% | | 58 | gpt-5-mini | 1105 ±80 | ~$0.32 | 56 | 14-19-23 | 73.3% | 8.4% | 42% | -0.3 | 43.7 | 3455 | 58s | 100% / 91.7% | | 59 | laguna-s-2.1 | 1103 ±107 | $0.18 | 25 | 4-6-15 | 77.3% | 6% | 28% | -9.2 | 39.8 | 24502 | 221s | 99.9% / 53.1% | | 60 | muse-spark-1.3-contributor | 1101 ±99 | $0.08 | 29 | 15-5-9 | 69.8% | 6.6% | 60.3% | +2.1 | 54.2 | 6916 | 72s | 100% / 91.9% | | 61 | grok-4.1-fast-reasoning ˟ | 1096 ±93 | ~$0.12 | 45 | 21-10-14 | 71.8% | 8.3% | 57.8% | +5.8 | 38.2 | 6137 | 105s | 100% / 78.6% | | 62 | gpt-5.1-chat ˟ | 1094 ±92 | ~$0.13 | 43 | 13-11-19 | 69.5% | 6.6% | 43% | -1.3 | 38.9 | 246 | 3.7s | 100% / 88.9% | | 63 | gpt-5-nano | 1093 ±86 | ~$0.15 | 54 | 20-19-15 | 72.1% | 7.5% | 54.6% | +3.9 | 42.1 | 8745 | 72s | 100% / 94.2% | | 64 | claude-opus-4.7 | 1092 ±78 | ~$0.66 | 59 | 20-19-20 | 67.6% | 8.4% | 50% | -0.7 | 43 | 362 | 5.4s | 99.7% / 72.5% | | 65 | claude-opus-5 | 1082 ±91 | $1.48 | 42 | 16-8-18 | 73% | 7.3% | 47.6% | +0.9 | 43.8 | 1142 | 18s | 100% / 93.4% | | 66 | claude-haiku-5.5 | 1080 ±100 | $0.04 | 30 | 8-6-16 | 71.1% | 8.5% | 36.7% | -3.5 | 40.1 | 1522 | 8.1s | 100% / 80.3% | | 67 | grok-4.6 | 1079 ±103 | $1.18 | 27 | 9-7-11 | 70.1% | 7.2% | 46.3% | +0.9 | 48.4 | 3556 | 67s | 100% / 83.5% | | 68 | qwen3.7-max | 1077 ±82 | ~$1.02 | 47 | 20-16-11 | 67.7% | 8.7% | 59.6% | +4.8 | 45.3 | 3849 | 62s | 100% / 91.1% | | 69 | kimi-k2.7-code | 1076 ±93 | ~$2.18 | 33 | 9-11-13 | 69.8% | 8.6% | 43.9% | -3.1 | 41.6 | 12518 | 222s | 99.8% / 85.4% | | 70 | muse-spark-1.2 | 1069 ±80 | ~$1.18 | 41 | 16-16-9 | 70% | 7.6% | 58.5% | +3.3 | 49.4 | 5211 | 32s | 100% / 88.8% | | 71 | grok-4.7 | 1058 ±107 | $1.42 | 27 | 14-4-9 | 68% | 8.5% | 59.3% | +4 | 45.7 | 5733 | 88s | 100% / 92.5% | | 72 | gpt-5.4 | 1051 ±97 | ~$0.13 | 47 | 13-7-27 | 75% | 7% | 35.1% | -3.2 | 33.9 | 168 | 3.0s | 99.5% / 91.9% | | 73 | codex-mini ˟ | 1043 ±93 | ~$1.60 | 45 | 16-16-13 | 70.2% | 7.1% | 53.3% | +1.7 | 43.7 | 5399 | 42s | 100% / 66.3% | | 74 | gpt-4.1 | 1039 ±67 | ~$0.11 | 80 | 32-31-17 | 70.6% | 6.7% | 59.4% | +5.2 | 46.5 | 150 | 2.7s | 100% / 97.2% | | 75 | o4-mini ˟ | 1027 ±88 | ~$1.01 | 50 | 19-17-14 | 71.5% | 6.9% | 55% | +1.2 | 44.7 | 4488 | 64s | 100% / 78.9% | | 76 | grok-4-fast-reasoning ˟ | 1025 ±86 | ~$0.09 | 47 | 12-19-16 | 70% | 7.2% | 45.7% | +3.8 | 42.7 | 4390 | 39s | 100% / 71.5% | | 77 | gpt-6-luna | 1021 ±95 | $0.04 | 30 | 2-10-18 | 73.9% | 7.7% | 23.3% | -9 | 49.1 | 1466 | 18s | 99.9% / 83.3% | | 78 | deepseek-v3.2-speciale | 1000 ±93 | ~$0.55 | 36 | 13-11-12 | 68.7% | 7.2% | 51.4% | -1.4 | 48.5 | 21426 | 513s | 100% / 79.2% | | 79 | gpt-4.1-mini | 995 ±76 | $0.05 | 61 | 25-21-15 | 64% | 11.3% | 58.2% | -1.7 | 52.9 | 286 | 4.5s | 99.5% / 61.5% | | 80 | step-3.5-flash | 991 ±96 | ~$0.48 | 40 | 16-11-13 | 64.1% | 10.9% | 53.8% | +4.9 | 39.5 | 35402 | 165s | 100% / 72.1% | | 81 | gemini-2.5-pro | 990 ±73 | ~$0.93 | 77 | 22-22-33 | 69.9% | 7.5% | 42.9% | -0.6 | 41.9 | 2219 | 39s | 99.9% / 86.7% | | 82 | gpt-5.3-chat ˟ | 989 ±89 | ~$0.48 | 37 | 10-13-14 | 67.5% | 9.2% | 44.6% | -2.6 | 41.1 | 672 | 8.8s | 99.6% / 78.4% | | 83 | claude-opus-4.8 | 985 ±86 | ~$0.54 | 45 | 10-14-21 | 70.4% | 7.4% | 37.8% | -2.3 | 42.6 | 313 | 4.8s | 99.7% / 84.1% | | 84 | muse-glimmer-30b | 984 ±94 | $0.72 | 34 | 12-15-7 | 67.7% | 8.5% | 57.4% | +1.2 | 46.6 | 9387 | 133s | 100% / 78.1% | | 85 | gpt-4 ˟ | 974 ±102 | $1.43 | 32 | 12-9-11 | 67% | 8.8% | 51.6% | -0.2 | 55.6 | 142 | 4.7s | 98.8% / 94.8% | | 86 | gpt-4o-2024-11-20 | 964 ±85 | $0.13 | 54 | 19-15-20 | 65.5% | 9.9% | 49.1% | -0.1 | 48.6 | 134 | 1.9s | 99.8% / 96.7% | | 87 | muse-spark-1.2-contributor | 949 ±85 | $0.05 | 38 | 10-14-14 | 67.2% | 9.2% | 44.7% | -2.2 | 47.1 | 4744 | 38s | 100% / 90.8% | | 88 | muse-spark-1.1 | 948 ±88 | $1.05 | 41 | 15-11-15 | 65.5% | 9.4% | 50% | +1.5 | 46.9 | 4672 | 26s | 100% / 83.4% | | 89 | nemotron-3.5-super-vl | 920 ±105 | $0.20 | 23 | 3-8-12 | 67.5% | 12.7% | 30.4% | -5.7 | 48.4 | 10346 | 147s | 100% / 75.6% | | 90 | nemotron-3-super-120b-a12b | 908 ±118 | ~$1.82 | 15 | 5-7-3 | 65.5% | 10.2% | 56.7% | +2.3 | 55.9 | 30458 | 449s | 98.9% / 68% | | 91 | gpt-5.1-codex-mini ˟ | 905 ±103 | ~$0.60 | 33 | 10-7-16 | 67.9% | 7.9% | 40.9% | -1.7 | 38.4 | 4569 | 46s | 100% / 78.6% | | 92 | kimi-k2.5 | 891 ±75 | ~$0.78 | 51 | 11-21-19 | 64.2% | 12.1% | 42.2% | -2 | 43.5 | 5943 | 129s | 99.8% / 77.1% | | 93 | claude-opus-4.5 | 890 ±73 | ~$0.67 | 52 | 9-28-15 | 61.3% | 10.9% | 44.2% | -2.8 | 51.1 | 332 | 6.8s | 99.9% / 78.8% | | 94 | o1 ˟ | 878 ±120 | ~$9.54 | 18 | 2-6-10 | 64.4% | 7.7% | 27.8% | -6.6 | 46.7 | 3026 | 25s | 100% / 79.1% | | 95 | gpt-oss-20b | 870 ±74 | ~$0.11 | 53 | 17-24-12 | 64.9% | 10% | 54.7% | +3.5 | 48.4 | 14114 | 45s | 99.7% / 86% | | 96 | claude-opus-4.1 | 858 ±78 | ~$1.55 | 54 | 11-18-25 | 63.3% | 9.9% | 37% | -1.8 | 43.4 | 300 | 9.3s | 98.9% / 82.1% | | 97 | hy3-preview | 856 ±99 | ~$0.32 | 26 | 4-12-10 | 65.1% | 8.8% | 38.5% | -5.2 | 51.6 | 9390 | 105s | 99.5% / 83.7% | | 98 | gemma-4-26b-a4b-it | 853 ±77 | $0.01 | 40 | 10-26-4 | 61.3% | 12.5% | 57.5% | +4.2 | 49.2 | 369 | 7.5s | 99.4% / 51.8% | | 99 | qwen3.5-35b-a3b | 846 ±79 | ~$0.61 | 39 | 13-21-5 | 61.8% | 13.3% | 60.3% | +3.1 | 50.7 | 8065 | 67s | 99.9% / 69.3% | | 100 | gpt-oss-120b | 844 ±78 | ~$0.13 | 53 | 16-24-13 | 64.5% | 10% | 52.8% | +4.8 | 48.1 | 4364 | 33s | 99.8% / 87.4% | | 101 | glm-5.2 | 842 ±86 | ~$1.40 | 33 | 10-13-10 | 64.3% | 11.8% | 50% | +1.5 | 48.9 | 6112 | 94s | 99.9% / 78.7% | | 102 | qwen3.6-plus | 841 ±80 | $0.52 | 34 | 9-22-3 | 59.1% | 14.6% | 58.8% | +3 | 57.5 | 3911 | 74s | 100% / 76% | | 103 | seed-2.0-lite | 838 ±85 | ~$0.21 | 31 | 8-15-8 | 66.1% | 8.7% | 50% | -0.6 | 49.2 | 1649 | 43s | 100% / 57.6% | | 104 | gpt-5.2-chat ˟ | 838 ±91 | ~$0.49 | 39 | 8-13-18 | 64.3% | 9.6% | 37.2% | -3.7 | 41.2 | 686 | 11s | 99.7% / 80.4% | | 105 | qwen3.5-122b-a10b | 835 ±86 | ~$0.89 | 31 | 9-14-8 | 60.8% | 11.6% | 51.6% | +1.6 | 50.4 | 6406 | 58s | 99.9% / 68.7% | | 106 | seed-2.0-mini | 834 ±84 | $0.23 | 29 | 7-15-7 | 61.5% | 11.5% | 50% | -1 | 46.5 | 8650 | 196s | 100% / 52.2% | | 107 | claude-opus-4.6 | 826 ±70 | ~$0.68 | 60 | 11-28-21 | 59.6% | 11.4% | 41.7% | -4 | 46.8 | 398 | 10s | 99.9% / 80.4% | | 108 | qwen3.5-flash | 825 ±90 | ~$0.18 | 27 | 8-15-4 | 56% | 15.9% | 57.4% | +1.9 | 52.5 | 8459 | 59s | 100% / 65.9% | | 109 | gemini-2.5-flash | 819 ±73 | ~$0.06 | 61 | 16-25-20 | 64.4% | 9.1% | 46.7% | +0.1 | 55 | 343 | 5.0s | 98.5% / 90.2% | | 110 | gpt-4-turbo ˟ | 816 ±83 | ~$0.68 | 42 | 9-18-15 | 60.2% | 10.7% | 42.9% | +0.4 | 52.2 | 209 | 4.9s | 99.2% / 81.1% | | 111 | grok-code-fast-1 ˟ | 815 ±85 | ~$0.44 | 35 | 8-20-7 | 58% | 10.8% | 51.4% | +2.8 | 55.3 | 4283 | 32s | 99.8% / 54% | | 112 | qwen3.7-flash | 812 ±99 | $0.04 | 26 | 1-12-13 | 60.8% | 13.9% | 26.9% | -8.6 | 58.4 | 4282 | 31s | 100% / 59% | | 113 | gemini-2.0-flash-001 ˟ | 811 ±64 | ~$0.008 | 72 | 15-34-23 | 59% | 13.9% | 44.4% | -0.4 | 59 | 193 | 1.6s | 100% / 88.2% | | 114 | mimo-v2.5-pro | 811 ±96 | ~$1.34 | 23 | 4-17-2 | 55.5% | 14.7% | 54.3% | +0.3 | 60 | 6677 | 100s | 100% / 71.4% | | 115 | qwen3.6-flash | 803 ±119 | $0.24 | 22 | 1-7-14 | 61.7% | 13.5% | 20.5% | -9.5 | 42.9 | 3764 | 28s | 100% / 58.5% | | 116 | qwen3.6-35b-a3b | 803 ±88 | ~$0.31 | 27 | 6-12-9 | 58% | 13.6% | 44.4% | -5.2 | 44.7 | 4205 | 43s | 99.9% / 63.5% | | 117 | nemotron-3-nano-30b-a3b | 795 ±76 | ~$0.23 | 43 | 12-24-7 | 65.2% | 11.5% | 55.8% | +3.3 | 55.4 | 15623 | 52s | 99.5% / 49.1% | | 118 | deepseek-v4-flash | 793 ±84 | ~$0.10 | 34 | 6-18-10 | 60.4% | 10.4% | 44.1% | -2.8 | 52.9 | 6048 | 82s | 99.9% / 71.2% | | 119 | o1-mini ˟ | 792 ±86 | ~$0.36 | 32 | 8-15-9 | 58.9% | 13% | 48.4% | -3 | 54.4 | 1327 | 16s | 100% / 72% | | 120 | claude-opus-4 ˟ | 787 ±78 | ~$1.86 | 49 | 7-26-16 | 59.7% | 11.2% | 40.8% | -0.5 | 54.7 | 299 | 9.1s | 99.2% / 87.9% | | 121 | mimo-v2-omni | 787 ±87 | ~$0.77 | 29 | 9-14-6 | 56.2% | 14.1% | 55.2% | +2.7 | 51.7 | 5921 | 46s | 99.8% / 62.3% | | 122 | deepseek-v4-pro | 786 ±93 | ~$1.12 | 33 | 8-12-13 | 59.3% | 12.7% | 42.4% | -5.8 | 45.5 | 10253 | 217s | 99.9% / 79.4% | | 123 | gemma-4-31b-it | 783 ±76 | ~$0.007 | 43 | 10-20-13 | 59.9% | 13.6% | 46.5% | +3.7 | 37.7 | 171 | 19s | 99.7% / 63.6% | | 124 | qwen3.5-9b | 783 ±100 | ~$0.17 | 22 | 6-14-2 | 57.3% | 10.6% | 59.1% | +5.7 | 53.2 | 19736 | 100s | 99.5% / 59.7% | | 125 | gpt-4o-mini | 773 ±81 | $0.03 | 41 | 10-17-14 | 60.1% | 13.2% | 45.1% | -2.4 | 52.4 | 474 | 6.1s | 99.7% / 51.4% | | 126 | qwen3.5-397b-a17b | 772 ±81 | ~$0.73 | 33 | 8-17-8 | 59.6% | 15.1% | 50% | -1.1 | 50.4 | 3904 | 70s | 100% / 83.7% | | 127 | minimax-m2 | 758 ±83 | ~$0.69 | 37 | 3-19-15 | 60.3% | 12.2% | 33.8% | -6.3 | 47.1 | 10768 | 132s | 98.9% / 56.8% | | 128 | laguna-m.1 | 758 ±138 | ~$0.19 | 7 | 2-3-2 | 58.6% | 13.8% | 50% | -1.1 | 50 | 6690 | 225s | 100% / 59.5% | | 129 | glm-5 | 755 ±81 | ~$1.26 | 37 | 4-23-10 | 59.8% | 11% | 41.9% | -2.2 | 57.6 | 6154 | 144s | 100% / 75.3% | | 130 | qwen3.5-27b | 750 ±83 | ~$0.93 | 29 | 7-17-5 | 56.2% | 17.2% | 53.4% | +3.6 | 47 | 7523 | 92s | 100% / 68.4% | | 131 | qwen3.6-27b | 749 ±90 | ~$1.45 | 24 | 5-11-8 | 59.8% | 12.4% | 43.8% | -1.3 | 45.3 | 10645 | 208s | 100% / 72% | | 132 | seed-oss-36b-instruct | 747 ±108 | ~$0.30 | 16 | 5-8-3 | 57% | 11.9% | 56.3% | -2.4 | 54.4 | 6914 | 37s | 100% / n/a | | 133 | gemini-1.5-pro ˟ | 746 ±102 | ~$0.12 | 22 | 3-13-6 | 58.6% | 11.9% | 43.2% | -0.3 | 57.9 | 187 | 5.5s | 93.4% / 75.6% | | 134 | step-3.7-flash | 741 ±111 | $1.68 | 18 | 4-8-6 | 56.6% | 15.7% | 44.4% | -2.6 | 43.8 | 26494 | 183s | 99.8% / 64.5% | | 135 | qwen3-14b | 741 ±88 | ~$0.10 | 25 | 4-18-3 | 56% | 13.5% | 52% | -1.7 | 61.5 | 4910 | 105s | 99.8% / 50.6% | | 136 | qwen3.5-plus-02-15 | 741 ±83 | ~$0.13 | 30 | 8-19-3 | 52.5% | 14.9% | 58.3% | +1.4 | 54.2 | 887 | 16s | 99.2% / 68.9% | | 137 | glm-5.1 | 740 ±88 | ~$1.75 | 29 | 6-14-9 | 56.8% | 15% | 44.8% | -2.4 | 49.4 | 7809 | 153s | 100% / 81.6% | | 138 | claude-sonnet-4.6 | 737 ±80 | $0.56 | 45 | 7-20-18 | 55.9% | 13.9% | 37.8% | -4.7 | 50.2 | 466 | 7.6s | 99.5% / 68.7% | | 139 | qwen3-8b | 728 ±100 | ~$0.11 | 21 | 5-16-0 | 56.9% | 9.5% | 61.9% | +6.9 | 61.8 | 7301 | 137s | 98.9% / 39% | | 140 | kimi-k2 | 728 ±69 | $0.05 | 55 | 9-30-16 | 56.2% | 14.7% | 43.6% | -2.9 | 54.7 | 303 | 9.0s | 96.8% / 69.5% | | 141 | mimo-v2.5 | 728 ±95 | ~$0.85 | 22 | 5-14-3 | 53.8% | 13.7% | 54.5% | +0.5 | 61.5 | 6059 | 63s | 100% / 64.7% | | 142 | ling-3.0-flash | 721 ±119 | $0.03 | 13 | 2-8-3 | 59.1% | 14.9% | 46.2% | -0.1 | 60.8 | 2680 | 12s | 94% / 51% | | 143 | grok-3-mini ˟ | 720 ±70 | ~$0.11 | 50 | 14-25-11 | 53.7% | 14.8% | 53% | +1 | 44.9 | 1544 | 15s | 100% / 60.5% | | 144 | gpt-5.4-nano | 716 ±97 | ~$0.03 | 22 | 3-16-3 | 55.6% | 11.3% | 50% | +0.7 | 69.1 | 190 | 2.3s | 98.3% / 38.2% | | 145 | north-mini-code | 715 ±86 | - | 29 | 5-20-4 | 52.7% | 18% | 51.7% | -1.1 | 56.8 | 17256 | 157s | 99.8% / 45.9% | | 146 | o3-mini ˟ | 714 ±87 | ~$1.00 | 30 | 3-15-12 | 61.3% | 10.2% | 35% | -5.6 | 49.9 | 2960 | 40s | 100% / 56.6% | | 147 | seed-1.6 | 714 ±87 | ~$0.13 | 29 | 5-15-9 | 57% | 12.8% | 43.1% | +1.7 | 44.3 | 1024 | 26s | 100% / 46.9% | | 148 | qwen3-next-80b-a3b-thinking | 714 ±84 | ~$0.74 | 30 | 8-17-5 | 50.5% | 15.3% | 55% | -0.5 | 49.1 | 9830 | 54s | 99.1% / 50.6% | | 149 | nemotron-3-ultra-550b-a55b | 707 ±110 | ~$1.11 | 17 | 4-7-6 | 55.8% | 16% | 44.1% | -3.1 | 55.6 | 4982 | 166s | 98.8% / 60.9% | | 150 | nemotron-3.5-lightning | 706 ±108 | $0.06 | 22 | 0-10-12 | 59.5% | 14.5% | 22.7% | -11.6 | 52.5 | 6288 | 65s | 99.9% / 39.3% | | 151 | mimo-v2-pro ˟ | 706 ±85 | ~$1.67 | 26 | 4-21-1 | 58.4% | 12.2% | 55.8% | +2.2 | 64.5 | 7179 | 100s | 100% / 66.4% | | 152 | longcat-2.0 | 703 ±96 | ~$2.88 | 23 | 3-13-7 | 54.8% | 12.3% | 41.3% | -2.9 | 64.2 | 26931 | 293s | 99.7% / 60.6% | | 153 | kimi-k2-thinking | 703 ±83 | ~$2.36 | 36 | 8-18-10 | 54.5% | 12.9% | 47.2% | -1.4 | 52.4 | 10551 | 284s | 100% / 69% | | 154 | claude-haiku-4.5 | 697 ±77 | $0.15 | 46 | 7-20-19 | 56.2% | 15% | 37% | -5.8 | 48.6 | 313 | 2.9s | 98.6% / 51.6% | | 155 | deepseek-v3.2 | 694 ±76 | ~$0.01 | 37 | 9-23-5 | 48.9% | 16.9% | 55.4% | -0.4 | 53.5 | 234 | 15s | 100% / 62.1% | | 156 | minimax-m3 | 694 ±110 | $1.04 | 20 | 9-5-6 | 48.7% | 15.2% | 57.5% | +5.5 | 44.3 | 16042 | 290s | 99.8% / 71.7% | | 157 | gpt-5.4-mini | 688 ±98 | ~$0.10 | 22 | 3-12-7 | 54.2% | 14.4% | 40.9% | -3.2 | 52.1 | 223 | 6.9s | 99.6% / 41.9% | | 158 | grok-2-latest ˟ | 687 ±90 | ~$0.20 | 24 | 3-20-1 | 52.7% | 11.8% | 54.2% | +3.5 | 62.9 | 151 | 4.4s | 98.3% / 67.1% | | 159 | laguna-xs-2.1 | 685 ±104 | ~$0.09 | 20 | 1-10-9 | 51.6% | 13.2% | 30% | -7 | 51.9 | 6716 | 100s | 96.7% / 51.2% | | 160 | gemini-2.5-flash-lite | 682 ±74 | ~$0.03 | 50 | 12-22-16 | 59.8% | 14.1% | 46% | +1.2 | 50.9 | 866 | 2.0s | 85.4% / 86.7% | | 161 | grok-4-fast-non-reasoning ˟ | 681 ±78 | ~$0.02 | 38 | 5-27-6 | 53.7% | 12.7% | 48.7% | +0.4 | 61.7 | 248 | 1.9s | 97.4% / 54.6% | | 162 | qwen3-plus-07-28 | 679 ±85 | ~$0.04 | 32 | 2-21-9 | 58.9% | 11.9% | 39.1% | -5 | 57.4 | 277 | 4.6s | 98.9% / 67.3% | | 163 | grok-3 ˟ | 678 ±78 | ~$0.29 | 39 | 5-26-8 | 54% | 12.9% | 46.2% | +0.9 | 56.6 | 212 | 5.9s | 100% / 84.1% | | 164 | ling-2.6-1t | 677 ±105 | ~$0.18 | 24 | 2-10-12 | 54% | 17.5% | 29.2% | -10 | 43.7 | 8041 | 57s | 99.6% / 57.4% | | 165 | internvl3-78b | 675 ±112 | ~$0.02 | 13 | 1-12-0 | 54.7% | 14.6% | 53.8% | +5.3 | 81.4 | 246 | 4.2s | 96.6% / 45.2% | | 166 | claude-sonnet-4 | 675 ±69 | ~$0.44 | 54 | 5-31-18 | 50.6% | 13.7% | 38% | -2.4 | 53.6 | 315 | 4.9s | 100% / 71.1% | | 167 | qwen3.7-plus | 673 ±106 | ~$0.50 | 20 | 3-8-9 | 53.8% | 15.3% | 35% | -5.3 | 50.3 | 5683 | 105s | 100% / 80.6% | | 168 | llama-3.3-70b-instruct | 673 ±59 | ~$0.02 | 70 | 14-42-14 | 50% | 20.4% | 50% | -1.4 | 59.6 | 307 | 8.9s | 99.2% / 49.5% | | 169 | kimi-k2-0905 | 672 ±72 | ~$0.06 | 52 | 8-26-18 | 49% | 15.7% | 40.4% | -2.5 | 52.4 | 271 | 8.0s | 98.4% / 69.5% | | 170 | claude-3.7-sonnet ˟ | 671 ±73 | ~$0.67 | 41 | 4-31-6 | 49.6% | 15.5% | 47.6% | -0.6 | 60.2 | 457 | 6.0s | 100% / 77.3% | | 171 | minimax-m2.1 | 664 ±94 | ~$0.79 | 23 | 1-13-9 | 55.9% | 12.6% | 32.6% | -8 | 58.1 | 6174 | 63s | 85.6% / 47.8% | | 172 | claude-sonnet-4.5 | 659 ±72 | ~$0.39 | 51 | 11-23-17 | 55.6% | 11.3% | 44.1% | -0.6 | 46.6 | 354 | 7.0s | 98.9% / 76% | | 173 | deepseek-r1-0528 | 656 ±98 | ~$1.55 | 20 | 2-15-3 | 56.1% | 11.7% | 47.5% | -1.1 | 62.8 | 7509 | 207s | 99.6% / 61.3% | | 174 | command-a | 656 ±87 | ~$0.44 | 28 | 3-19-6 | 54.6% | 19% | 44.6% | +2.8 | 64.5 | 321 | 4.8s | 98.6% / 45.9% | | 175 | mistral-large-2-2411 | 655 ±69 | ~$0.43 | 48 | 9-31-8 | 47.6% | 18.3% | 51% | -1.5 | 70.9 | 403 | 10s | 88% / 52.3% | | 176 | qwen2.5-72b-instruct | 653 ±68 | ~$0.03 | 49 | 8-34-7 | 54% | 13.3% | 51% | +1.4 | 74.6 | 408 | 7.4s | 95.4% / 53% | | 177 | deepseek-r1 | 652 ±101 | ~$1.05 | 19 | 6-11-2 | 48.3% | 16.8% | 60.5% | -1.5 | 50.1 | 5824 | 169s | 100% / 61.9% | | 178 | longcat-flash-chat | 649 ±81 | ~$0.02 | 32 | 7-18-7 | 48.3% | 15.5% | 50% | -2.3 | 51.4 | 342 | 4.6s | 98.7% / 65.9% | | 179 | gemma-2-27b-it | 643 ±81 | ~$0.04 | 32 | 3-23-6 | 51.5% | 19.2% | 45.3% | -2.8 | 58.6 | 193 | 4.6s | 92% / 44.3% | | 180 | qwen3-max | 642 ±84 | ~$0.23 | 34 | 4-20-10 | 52.3% | 17% | 41.2% | -3.3 | 62.2 | 389 | 10s | 99.9% / 62.3% | | 181 | minimax-m1 | 641 ±120 | ~$1.44 | 16 | 2-7-7 | 56.4% | 12% | 34.4% | -4.6 | 58.3 | 9059 | 496s | 99.7% / 46.8% | | 182 | devstral-2512 | 641 ±90 | ~$0.09 | 27 | 6-13-8 | 53.2% | 13.6% | 46.3% | -1.3 | 57.2 | 532 | 3.5s | 98.1% / 61.2% | | 183 | qwen3-235b-a22b | 641 ±88 | ~$0.48 | 30 | 6-12-12 | 52.7% | 16.8% | 40% | -4.7 | 47.3 | 7579 | 141s | 99.5% / 49.7% | | 184 | qwen3-235b-a22b-thinking-2507 | 640 ±96 | ~$1.28 | 22 | 1-18-3 | 48.2% | 14.8% | 45.5% | -4.1 | 65.2 | 9081 | 145s | 99.7% / 57.1% | | 185 | ministral-14b-2512 | 635 ±102 | $0.03 | 19 | 3-11-5 | 55.9% | 18.2% | 44.7% | -0.8 | 69.1 | 513 | 4.1s | 88.8% / 37.6% | | 186 | ernie-4.5-21b-a3b-thinking | 634 ±121 | ~$0.20 | 13 | 5-7-1 | 46.5% | 16.5% | 65.4% | +1.7 | 70.7 | 9531 | 101s | 98% / n/a | | 187 | olmo-3-32b-think | 634 ±110 | ~$0.31 | 16 | 7-8-1 | 43.3% | 16.8% | 68.8% | +2.6 | 58.4 | 12353 | 208s | 99.9% / 42.2% | | 188 | deepseek-v3.2-exp | 633 ±88 | ~$0.01 | 25 | 4-14-7 | 50.2% | 14% | 44% | +0.4 | 46.6 | 259 | 10.0s | 99.2% / 56.2% | | 189 | deepseek-v3 | 631 ±79 | $0.04 | 31 | 3-23-5 | 51.5% | 17.7% | 46.8% | +0.3 | 57.1 | 279 | 8.2s | 99.8% / 67.2% | | 190 | minimax-m2.7 | 630 ±102 | $0.73 | 18 | 1-9-8 | 54.1% | 15.2% | 30.6% | -5.8 | 67 | 6482 | 154s | 93.4% / 63.3% | | 191 | intellect-3 | 628 ±134 | ~$0.60 | 10 | 3-6-1 | 49.1% | 14.2% | 60% | +2.4 | 74.2 | 7173 | 76s | 99.6% / n/a | | 192 | inflection-3-pi | 628 ±116 | ~$0.22 | 13 | 4-9-0 | 48.5% | 16.7% | 65.4% | +4.8 | 71.4 | 115 | 4.2s | 92.9% / 62.1% | | 193 | mistral-large-4.0 | 627 ±101 | $0.12 | 21 | 2-9-10 | 54.9% | 14.9% | 31% | -4.5 | 52.6 | 683 | 16s | 99.6% / 60.4% | | 194 | lfm-7b ˟ | 625 ±79 | ~<$0.001 | 36 | 1-27-8 | 47.4% | 24.1% | 40.3% | -8.6 | 85.1 | 85 | 8.4s | 81.6% / n/a | | 195 | qwen3-coder-next | 624 ±96 | ~$0.15 | 20 | 4-14-2 | 44.5% | 17.7% | 55% | +1.3 | 65.8 | 1533 | 8.4s | 95.9% / 46.6% | | 196 | qwen3-32b | 621 ±81 | ~$0.18 | 36 | 8-17-11 | 52.7% | 15.5% | 45.8% | -1.6 | 54.6 | 4322 | 99s | 99.8% / 40.1% | | 197 | deepseek-v3-0324 | 618 ±74 | ~$0.02 | 41 | 5-26-10 | 53.5% | 14.3% | 43.9% | -1.3 | 56.6 | 177 | 9.5s | 99.6% / 67.8% | | 198 | gemini-2.0-flash-lite-001 ˟ | 615 ±83 | ~$0.005 | 34 | 5-17-12 | 52.9% | 14.4% | 39.7% | -0.2 | 59.7 | 76 | 2.2s | 97.9% / 62.4% | | 199 | seed-1.6-flash | 614 ±88 | ~$0.17 | 28 | 2-19-7 | 48.7% | 16.8% | 41.1% | -6.1 | 68.9 | 6361 | 40s | 99.1% / 40.8% | | 200 | llama-3.1-nemotron-ultra-253b-v1 | 610 ±107 | ~$0.48 | 15 | 2-10-3 | 51.3% | 15.8% | 46.7% | -1.5 | 71.3 | 2301 | 11s | 100% / 55% | | 201 | mistral-large-3-2512 | 609 ±81 | ~$0.10 | 33 | 11-16-6 | 44.9% | 21.3% | 57.6% | -0.4 | 74.7 | 434 | 10s | 99.6% / 58.1% | | 202 | ling-2.6-flash | 604 ±103 | ~$0.01 | 25 | 0-9-16 | 52.5% | 13.7% | 18% | -12.3 | 43.7 | 1544 | 10s | 95.5% / 49.4% | | 203 | llama-3.3-nemotron-super-49b-v1.5 | 603 ±119 | ~$0.38 | 12 | 1-10-1 | 47.9% | 12.9% | 50% | -3.3 | 74.4 | 7945 | 79s | 100% / 41% | | 204 | claude-3-sonnet ˟ | 602 ±139 | ~$0.41 | 7 | 2-4-1 | 49.1% | 16.6% | 57.1% | +6.4 | 106 | 258 | 15s | - | | 205 | qwen2.5-max ˟ | 602 ±81 | ~$0.39 | 31 | 4-20-7 | 46.6% | 18.4% | 45.2% | -1.8 | 61.9 | 454 | 10s | 97.8% / 45.5% | | 206 | phi-4 | 601 ±93 | ~$0.01 | 23 | 6-14-3 | 43% | 25.6% | 56.5% | +2.5 | 71.3 | 344 | 7.4s | 79.3% / 48.7% | | 207 | glm-4.5 | 601 ±79 | ~$0.31 | 32 | 5-23-4 | 42.9% | 21.6% | 51.6% | -1.3 | 64.3 | 1798 | 27s | 98.1% / 52% | | 208 | claude-3.5-sonnet ˟ | 600 ±92 | ~$0.38 | 25 | 5-11-9 | 50.2% | 16% | 42% | -3.6 | 51.4 | 286 | 6.0s | 97.6% / 82.6% | | 209 | magistral-medium-2506 | 598 ±142 | ~$0.18 | 10 | 2-4-4 | 51% | 13.8% | 40% | -1.5 | 78.9 | 122 | 2.0s | 97.7% / n/a | | 210 | minimax-m2.5 | 597 ±105 | ~$0.61 | 17 | 3-10-4 | 43.4% | 21.9% | 47.1% | -1.1 | 66.4 | 4807 | 117s | 96% / 54.9% | | 211 | deepseek-v3.1-terminus | 594 ±109 | ~$0.02 | 16 | 5-7-4 | 47.1% | 13.8% | 53.1% | +1.2 | 54.8 | 166 | 5.1s | 98.5% / 70.3% | | 212 | hunyuan-a13b-instruct | 593 ±89 | ~$0.04 | 25 | 2-14-9 | 53.6% | 17.5% | 36% | -13.6 | 61.8 | 482 | 5.7s | 71.8% / 37.8% | | 213 | grok-4.20-non-reasoning | 589 ±94 | ~$0.14 | 26 | 1-14-11 | 48.9% | 14.2% | 30.8% | -2.9 | 53.6 | 208 | 1.4s | 99.5% / 63.1% | | 214 | glm-4.6v | 588 ±84 | ~$0.26 | 28 | 3-22-3 | 47.3% | 20% | 50% | -2.6 | 78.8 | 2123 | 42s | 99.7% / 42.6% | | 215 | qwen3-30b-a3b | 587 ±95 | ~$0.19 | 22 | 2-18-2 | 48.2% | 14.5% | 50% | +0.1 | 73 | 6245 | 75s | 100% / 39.8% | | 216 | devstral-medium | 584 ±122 | ~$0.10 | 13 | 4-8-1 | 44.2% | 17.8% | 61.5% | +0.8 | 75 | 486 | 1.7s | 94.8% / n/a | | 217 | gemma-3-12b-it | 582 ±94 | ~$0.01 | 22 | 3-16-3 | 43.9% | 24.5% | 50% | -3.7 | 57 | 424 | 7.1s | 99.2% / 39.9% | | 218 | grok-4.1-fast-non-reasoning ˟ | 580 ±90 | ~$0.02 | 27 | 3-15-9 | 45.1% | 19.7% | 38.9% | -5.6 | 55 | 290 | 2.5s | 99.5% / 48.1% | | 219 | llama-3.3-nemotron-super-49b-v1 | 577 ±123 | ~$0.01 | 11 | 2-9-0 | 46.4% | 19.9% | 59.1% | +6.1 | 89.3 | 155 | 5.2s | 89.3% / n/a | | 220 | qwen3-coder-plus | 576 ±94 | $0.12 | 22 | 0-16-6 | 46% | 18.8% | 36.4% | -4.6 | 65.5 | 207 | 5.0s | 99% / 53.3% | | 221 | gemini-1.5-flash ˟ | 576 ±110 | ~$0.004 | 13 | 2-10-1 | 43.5% | 21.1% | 53.8% | +5.6 | 49.3 | 276 | 2.6s | - | | 222 | qwen3-next-80b-a3b-instruct | 575 ±83 | ~$0.03 | 32 | 2-19-11 | 46.6% | 17.2% | 35.9% | -3.3 | 53.5 | 365 | 3.1s | 92% / 52.6% | | 223 | gpt-4.1-nano ˟ | 574 ±84 | ~$0.03 | 29 | 2-20-7 | 47.3% | 17.3% | 41.4% | -3.6 | 72.1 | 352 | 6.4s | 94.3% / 27.2% | | 224 | ling-1t | 574 ±113 | ~$0.07 | 17 | 5-7-5 | 44.2% | 19.5% | 50% | -0.6 | 48.2 | 199 | 7.0s | 90.7% / n/a | | 225 | glm-4.6 | 572 ±78 | ~$0.44 | 34 | 4-24-6 | 45.7% | 18.6% | 47.1% | -1 | 62.6 | 2576 | 31s | 97.3% / 52.5% | | 226 | qwen3-vl-235b-a22b-thinking | 571 ±118 | ~$1.13 | 12 | 2-8-2 | 46.5% | 16.6% | 50% | +0.7 | 60.3 | 4120 | 80s | 100% / 55.2% | | 227 | qwen2.5-plus ˟ | 570 ±88 | ~$0.05 | 24 | 6-16-2 | 43.7% | 17.5% | 58.3% | +5.1 | 72.3 | 352 | 6.8s | 98.5% / 60.9% | | 228 | qwq-32b | 566 ±120 | ~$0.17 | 14 | 1-8-5 | 45.5% | 15.7% | 35.7% | -6.4 | 63.1 | 5078 | 150s | 98.2% / 41.8% | | 229 | lfm2-8b-a1b | 565 ±98 | ~$0.009 | 21 | 7-14-0 | 41.1% | 22.5% | 66.7% | +9.6 | 97.5 | 403 | 1.6s | 91.4% / 32.5% | | 230 | lfm-2-24b-a2b | 563 ±120 | ~$0.004 | 17 | 0-8-9 | 53.5% | 18.3% | 23.5% | -14.9 | 59.5 | 112 | 1.5s | 54.8% / 33.5% | | 231 | claude-3.5-haiku ˟ | 562 ±91 | ~$0.08 | 25 | 1-17-7 | 57% | 18.2% | 38% | -5.6 | 60.2 | 137 | 3.9s | 100% / 46.3% | | 232 | inflection-3-productivity | 562 ±118 | ~$0.33 | 12 | 2-9-1 | 45.4% | 20.8% | 54.2% | +4.3 | 89.4 | 158 | 4.4s | 93.3% / 58.4% | | 233 | llama-3.1-70b-instruct | 561 ±109 | ~$0.05 | 16 | 1-13-2 | 46.7% | 21.5% | 46.9% | -2.6 | 70.2 | 505 | 6.9s | 98.8% / 51.6% | | 234 | ministral-8b | 560 ±99 | ~$0.009 | 21 | 2-18-1 | 51.8% | 16.7% | 52.4% | +11.4 | 60.6 | 46 | 2.3s | 57.7% / n/a | | 235 | glm-4.7-flash | 557 ±118 | $0.96 | 13 | 1-7-5 | 48.2% | 18.6% | 34.6% | -4.2 | 72.7 | 25334 | 446s | 97.7% / 39.8% | | 236 | llama-4-maverick | 556 ±75 | ~$0.04 | 41 | 7-21-13 | 45.2% | 17.6% | 42.7% | -2.7 | 67.2 | 341 | 4.2s | 99.4% / 49.6% | | 237 | mimo-v2-flash | 556 ±82 | ~$0.05 | 31 | 1-25-5 | 43.1% | 21.2% | 43.5% | -1.5 | 65.1 | 2066 | 6.9s | 96.8% / 66.7% | | 238 | llama-3.1-405b-instruct | 554 ±76 | ~$0.29 | 35 | 4-21-10 | 44.4% | 16.8% | 41.4% | -2.4 | 73.5 | 425 | 15s | 97.1% / 62.9% | | 239 | nova-2-lite-v1 | 553 ±117 | $0.05 | 14 | 1-10-3 | 47.4% | 15.3% | 42.9% | -2.9 | 81.1 | 142 | 1.7s | 98.2% / n/a | | 240 | qwen3-vl-8b-instruct | 552 ±123 | ~$0.02 | 12 | 1-10-1 | 43% | 20.4% | 50% | 0 | 67.9 | 519 | 3.1s | 96.3% / n/a | | 241 | qwen3-30b-a3b-thinking-2507 | 550 ±114 | ~$0.28 | 14 | 1-12-1 | 45.3% | 16.7% | 50% | +0.1 | 86.8 | 5661 | 52s | 100% / 41% | | 242 | deepseek-v3.1 | 550 ±86 | ~$0.04 | 28 | 5-14-9 | 45% | 20.7% | 42.9% | -1.2 | 65.3 | 294 | 11s | 99.6% / 71% | | 243 | qwen3-coder-480b-a35b | 546 ±94 | ~$0.19 | 22 | 4-13-5 | 45.1% | 21% | 47.7% | -1.1 | 68.6 | 1263 | 10s | 94.2% / 58.4% | | 244 | glm-4.5-air | 543 ±90 | ~$0.03 | 27 | 7-15-5 | 41.1% | 21.7% | 53.7% | -4.3 | 63.2 | 300 | 16s | 96.7% / 41.4% | | 245 | mistral-small-4-119b-a6b | 542 ±83 | $0.04 | 28 | 5-19-4 | 41.7% | 19.7% | 51.8% | +1 | 87.4 | 363 | 3.0s | 86.8% / 41.2% | | 246 | ernie-4.5-21b-a3b | 541 ±94 | ~$0.05 | 21 | 2-17-2 | 45.5% | 19.8% | 50% | +3.4 | 78.9 | 1154 | 3.6s | 88.6% / 38.9% | | 247 | gemini-1.5-flash-8b ˟ | 539 ±120 | ~<$0.001 | 11 | 1-8-2 | 42.6% | 21.1% | 45.5% | +3.6 | 43.3 | 95 | 1.0s | 89.5% / n/a | | 248 | jamba-large-1.7 | 537 ±92 | ~$0.51 | 24 | 3-14-7 | 44.2% | 21% | 41.7% | -7.9 | 69.6 | 352 | 9.5s | 99.4% / 43.3% | | 249 | glm-4-32b | 534 ±86 | ~$0.02 | 26 | 4-17-5 | 44.8% | 20.1% | 48.1% | +0.6 | 74.1 | 561 | 6.7s | 94.3% / 44% | | 250 | claude-3-haiku ˟ | 534 ±95 | ~$0.16 | 21 | 4-16-1 | 40.9% | 25.3% | 57.1% | -4.8 | 99.9 | 567 | 5.9s | 99.7% / 40.4% | | 251 | ernie-4.5-300b-a47b | 532 ±85 | ~$0.05 | 29 | 1-19-9 | 43% | 23% | 36.2% | -4.8 | 85.1 | 251 | 17s | 100% / 52.8% | | 252 | qwen3-30b-a3b-instruct-2507 | 529 ±82 | ~$0.05 | 30 | 4-20-6 | 44.8% | 21.9% | 46.7% | -3.2 | 61.1 | 684 | 7.9s | 95% / 35.9% | | 253 | mistral-medium-3.5 | 525 ±95 | $0.49 | 22 | 4-13-5 | 39.5% | 24.5% | 47.7% | +0.4 | 76.5 | 444 | 2.8s | 98% / 55.3% | | 254 | llama-4-scout | 523 ±75 | ~$0.03 | 37 | 2-27-8 | 42.9% | 22% | 41.9% | -7.9 | 73.1 | 342 | 5.1s | 100% / 41.8% | | 255 | claude-3-opus ˟ | 521 ±115 | ~$1.91 | 12 | 2-6-4 | 44.3% | 20% | 41.7% | -4.5 | 65.5 | 169 | 5.8s | 91.7% / 77.2% | | 256 | command-r-08-2024 | 520 ±97 | ~$0.04 | 21 | 2-11-8 | 45.1% | 22.6% | 35.7% | -9.4 | 82.2 | 303 | 7.1s | 84.2% / 42.2% | | 257 | qwen2.5-turbo ˟ | 517 ±88 | ~$0.01 | 24 | 3-19-2 | 41.3% | 22.5% | 52.1% | +4.3 | 89.2 | 298 | 7.2s | 95.8% / 40.1% | | 258 | qwen3-vl-32b-instruct | 516 ±144 | ~$0.03 | 12 | 4-2-6 | 43.1% | 22.8% | 41.7% | -7.2 | 49.8 | 306 | 5.3s | 99% / 54.9% | | 259 | qwen3-vl-235b-a22b-instruct | 513 ±116 | ~$0.09 | 13 | 0-8-5 | 43.7% | 24.8% | 30.8% | -3.2 | 68.5 | 555 | 11s | 100% / 74.4% | | 260 | gemma-2-9b-it | 513 ±98 | ~$0.007 | 21 | 3-14-4 | 40% | 20.1% | 47.6% | +0.2 | 90.8 | 148 | 1.4s | 70.9% / 40.6% | | 261 | gemma-3-27b-it | 512 ±86 | ~$0.009 | 32 | 1-15-16 | 49.9% | 20.1% | 26.6% | -7.9 | 50.6 | 296 | 7.4s | 95.3% / 49.1% | | 262 | mistral-small-3.2-24b-instruct | 511 ±94 | ~$0.01 | 20 | 1-17-2 | 43.5% | 23.4% | 47.5% | -5.2 | 81.1 | 303 | 4.7s | 97.8% / 43.5% | | 263 | command-r-plus-08-2024 | 508 ±94 | ~$0.98 | 20 | 2-15-3 | 37.7% | 29.8% | 47.5% | -4.4 | 85.5 | 480 | 16s | 88.2% / 43.1% | | 264 | devstral-small | 503 ±109 | ~$0.01 | 15 | 1-9-5 | 46.5% | 18.1% | 36.7% | -8.8 | 69.8 | 269 | 2.4s | 97.8% / 41.2% | | 265 | llama-3-8b-instruct | 503 ±116 | ~$0.005 | 14 | 0-12-2 | 44.8% | 23.3% | 42.9% | +0.4 | 111.6 | 76 | 1.9s | 88% / n/a | | 266 | mistral-medium-3 | 503 ±91 | ~$0.14 | 30 | 6-14-10 | 44.3% | 24.6% | 43.3% | -1.8 | 64.3 | 519 | 6.3s | 99.3% / 55.1% | | 267 | magistral-small-2506 | 503 ±115 | ~$0.06 | 13 | 3-5-5 | 42.2% | 19.4% | 42.3% | -10.3 | 70.5 | 205 | 1.8s | 98.5% / 45.6% | | 268 | mistral-small-3-24b-instruct-2501 | 503 ±95 | ~$0.007 | 20 | 5-13-2 | 37.3% | 28.3% | 57.5% | +0.5 | 84.4 | 351 | 6.4s | 97.7% / 51.8% | | 269 | molmo-2-8b | 502 ±122 | ~$0.02 | 12 | 2-7-3 | 44.6% | 20.5% | 45.8% | -3.8 | 93.1 | 97 | 1.4s | 91% / n/a | | 270 | llama-3.1-8b-instruct | 501 ±79 | ~$0.004 | 33 | 8-22-3 | 31.1% | 25.9% | 57.6% | -2.5 | 107 | 107 | 1.9s | 85.4% / 52.4% | | 271 | wizardlm-2-8x22b | 500 ±112 | ~$0.04 | 15 | 1-8-6 | 45.3% | 20.4% | 33.3% | -7.7 | 56.7 | 319 | 13s | 96.9% / 40.9% | | 272 | deepseek-prover-v2 | 498 ±112 | ~$0.05 | 12 | 1-7-4 | 43.6% | 18.7% | 37.5% | -3.3 | 63.9 | 171 | 18s | 98.4% / 65.1% | | 273 | jamba-large-1.6 | 495 ±115 | ~$0.22 | 11 | 1-7-3 | 41.4% | 29.3% | 40.9% | -6.2 | 87.8 | 112 | 8.5s | 98.3% / n/a | | 274 | mistral-nemo | 494 ±102 | ~$0.004 | 18 | 2-11-5 | 40.1% | 20.2% | 41.7% | +1.6 | 92 | 103 | 2.6s | 63.1% / 41.8% | | 275 | qwen3-4b | 493 ±163 | - | 5 | 1-4-0 | 39.7% | 25.5% | 60% | +5.8 | 66.8 | 5161 | 42s | 99.1% / n/a | | 276 | mistral-medium-3.1 | 493 ±81 | ~$0.16 | 29 | 4-19-6 | 39.5% | 23.9% | 46.6% | -3.8 | 78.6 | 537 | 11s | 97.3% / 47.2% | | 277 | qwen3-235b-a22b-instruct-2507 | 490 ±79 | ~$0.04 | 38 | 3-18-17 | 43.4% | 21% | 31.6% | -3.6 | 56.7 | 430 | 7.2s | 99.4% / 62.9% | | 278 | qwen2.5-7b-instruct | 482 ±110 | ~$0.006 | 16 | 1-13-2 | 43.1% | 22.9% | 46.9% | +8.8 | 82.9 | 80 | 2.7s | 88.5% / n/a | | 279 | mistral-small-3.1-24b-instruct | 482 ±94 | ~$0.01 | 22 | 3-14-5 | 37.2% | 27.8% | 45.5% | +0.5 | 69 | 326 | 3.0s | 97.1% / 49.6% | | 280 | olmo-3.1-32b-instruct | 481 ±116 | ~$0.04 | 14 | 1-7-6 | 43.9% | 29.3% | 32.1% | -12.1 | 71.3 | 483 | 8.4s | 98% / 46% | | 281 | ministral-8b-2512 | 481 ±105 | ~$0.02 | 17 | 2-10-5 | 41.2% | 21.4% | 41.2% | -1.1 | 75.6 | 561 | 2.8s | 91.9% / 36.7% | | 282 | llama-3.3-8b-instruct ˟ | 470 ±113 | - | 15 | 0-13-2 | 38.5% | 29.6% | 43.3% | -6.5 | 75.6 | 102 | 1.0s | 91.3% / n/a | | 283 | llama-3.2-3b-instruct | 467 ±112 | $0.009 | 15 | 0-14-1 | 43.1% | 20.3% | 46.7% | +3.5 | 100.8 | 123 | 1.5s | 60.9% / n/a | | 284 | rnj-1-instruct | 465 ±123 | ~$0.01 | 12 | 2-7-3 | 38.7% | 26.6% | 45.8% | +5.2 | 62.8 | 169 | 1.5s | 86.4% / n/a | | 285 | granite-4.0-h-micro | 457 ±118 | $0.002 | 13 | 0-13-0 | 39.7% | 24% | 50% | -0.7 | 62.9 | 133 | 4.6s | 77.4% / n/a | | 286 | gemma-3-4b-it | 457 ±112 | ~$0.003 | 15 | 0-15-0 | 37.5% | 26.5% | 50% | -2.1 | 78.5 | 93 | 2.1s | 76.2% / n/a | | 287 | mistral-small-creative ˟ | 457 ±113 | ~$0.03 | 15 | 3-8-4 | 35.1% | 23% | 46.7% | -0.5 | 72.8 | 1010 | 5.7s | 91.5% / n/a | | 288 | kimi-linear-48b-a3b-instruct | 456 ±103 | ~$0.12 | 16 | 1-11-4 | 34.3% | 25.3% | 40.6% | -2.6 | 86.7 | 689 | 4.2s | 84.5% / 32.6% | | 289 | mythomax-l2-13b | 453 ±120 | ~$0.02 | 13 | 0-9-4 | 41.1% | 23.8% | 34.6% | -13.4 | 87.2 | 142 | 4.0s | 69.5% / n/a | | 290 | olmo-2-0325-32b-instruct | 449 ±102 | ~$0.02 | 18 | 1-11-6 | 40.5% | 24.2% | 36.1% | -10.6 | 90.3 | 118 | 6.2s | 93.8% / 38.1% | | 291 | olmo-3-7b-think | 446 ±118 | ~$0.47 | 12 | 0-10-2 | 41.1% | 17.9% | 41.7% | -1.6 | 112.6 | 15512 | 112s | 98.8% / 31.5% | | 292 | lfm-2.2-6b | 446 ±119 | ~$0.02 | 14 | 2-8-4 | 34.6% | 21.9% | 42.9% | -0.3 | 110.2 | 379 | 0.9s | 57.2% / n/a | | 293 | afm-4.5b | 442 ±116 | ~$0.01 | 14 | 2-10-2 | 33.5% | 31.1% | 50% | -8.9 | 97.3 | 85 | 1.1s | 69.1% / n/a | | 294 | minimax-m2-her | 440 ±126 | $0.28 | 11 | 3-6-2 | 27.7% | 25.7% | 54.5% | +5.5 | 119.3 | 1339 | 8.8s | 82.3% / n/a | | 295 | ministral-3b ˟ | 439 ±106 | ~$0.004 | 17 | 2-14-1 | 32.2% | 34.4% | 52.9% | +6.9 | 65.6 | 46 | 0.6s | 52.3% / n/a | | 296 | jamba-mini-1.6 | 430 ±150 | ~$0.02 | 7 | 0-6-1 | 32% | 34.4% | 42.9% | -8.4 | 86 | 97 | 1.2s | 90.8% / n/a | | 297 | phi-3-medium-128k-instruct | 425 ±122 | ~$0.07 | 12 | 0-11-1 | 32.8% | 33.3% | 45.8% | -1.1 | 106.9 | 126 | 2.7s | 75% / n/a | | 298 | mistral-7b-instruct-v0.1 | 422 ±123 | ~$0.03 | 12 | 1-9-2 | 28.6% | 42% | 45.8% | -9.8 | 81.7 | 135 | 4.6s | 46.4% / n/a | | 299 | command-r7b-12-2024 | 420 ±98 | $0.01 | 21 | 1-16-4 | 34.3% | 27.6% | 42.9% | -3.8 | 126.1 | 224 | 3.4s | 81.5% / 38.2% | | 300 | olmo-3-7b-instruct | 419 ±114 | ~$0.02 | 18 | 3-7-8 | 36.1% | 23.5% | 36.1% | -6.9 | 78.7 | 394 | 4.3s | 88.6% / 30.5% | | 301 | jamba-mini-1.7 | 419 ±96 | ~$0.13 | 20 | 0-15-5 | 35.8% | 27.9% | 37.5% | -4.3 | 120 | 982 | 4.0s | 90.6% / 34.6% | | 302 | random-mover | 419 | - | 200 | 15-170-15 | 28.6% | 30.5% | 50% | 0 | 174.2 | - | - | 100% / 100% | | 303 | lfm-3b ˟ | 413 ±110 | ~$0.002 | 15 | 0-13-2 | 30.6% | 28.8% | 43.3% | +4.3 | 93.2 | 76 | 4.3s | 71.2% / n/a | | 304 | ministral-3b-2512 | 410 ±108 | $0.04 | 16 | 2-8-6 | 36.4% | 26.3% | 37.5% | -3.6 | 104.8 | 508 | 6.0s | 94.7% / 26.5% | | 305 | ui-tars-1.5-7b | 407 ±96 | ~$0.02 | 22 | 1-15-6 | 41.2% | 20% | 38.6% | +2.7 | 92.5 | 155 | 2.1s | 75.8% / 39.2% | | 306 | gemma-3n-e4b-it | 402 ±92 | ~$0.005 | 24 | 0-18-6 | 35.8% | 33.5% | 37.5% | -3.3 | 69.3 | 574 | 5.2s | 68.9% / 40.8% | ## Puzzle Rating: 100+ puzzles, Lichess set v1 (500 puzzles in set, 53 models) Puzzle Elo = maximum-likelihood performance rating vs. official Lichess puzzle ratings; only first-try solves count. Separate from game Elo. Correlates with reasoning Elo. Recover = % of first-try misses solved on the second try. Partial = % of solution moves found. Tok = output tokens per API call. Cost per puzzle. | # | Model | Puzzle Elo | Puzzles | 1st Try | Recover | Failed | Partial | Legal | Tok | Cost | Spd | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | gemini-4-argon-high | 2150 ±74 | 250/500 | 76% | 68.3% | 7.6% | 92.9% | 100% | 2679 | 7.44¢ | 43s | | 2 | gemini-3.7-flash ˟ | 2100 ±54 | 500 | 74.8% | 60.3% | 10% | 90.3% | 100% | 1278 | 1.31¢ | 12s | | 3 | gemini-3.8-flash | 2091 ±53 | 500 | 74.4% | 51.6% | 12.4% | 88% | 99.9% | 1329 | 1.34¢ | 14s | | 4 | gemini-3.1-pro-preview | 2060 ±81 | 200/500 | 72.5% | 41.8% | 16% | 84.8% | 100% | 11083 | 34.54¢ | 86s | | 5 | gemini-3.6-flash | 1963 ±52 | 500 | 68.2% | 46.5% | 17% | 84.2% | 100% | 1742 | 1.72¢ | 11s | | 6 | gpt-6-astra | 1921 ±71 | 250/500 | 64.4% | 55.1% | 16% | 84.6% | 100% | 1265 | 8.91¢ | 30s | | 7 | gemini-4-argon | 1843 ±51 | 500 | 62.2% | 54.5% | 17.2% | 84.7% | 100% | 451 | 1.47¢ | 9.4s | | 8 | deepseek-v4.1-flash-1017 | 1760 ±81 | 200/500 | 57% | 31.4% | 29.5% | 70.8% | 100% | 47395 | 6.82¢ | 267s | | 9 | gpt-6.1-sol | 1736 ±51 | 500 | 56.8% | 39.4% | 26.2% | 76.1% | 100% | 1081 | 1.50¢ | 27s | | 10 | claude-opus-5.5 | 1631 ±72 | 250/500 | 49.2% | 32.3% | 34.4% | 69.3% | 99.7% | 1234 | 7.23¢ | 17s | | 11 | gemini-3-flash-preview | 1630 ±51 | 500 | 51.4% | 32.9% | 32.6% | 70.1% | 99.5% | 106 | 0.12¢ | 1.9s | | 12 | hy3 | 1616 ±72 | 250/500 | 48.4% | 35.7% | 33.2% | 67.4% | 100% | 18758 | 2.79¢ | 167s | | 13 | deepseek-v4-flash-0731 | 1600 ±81 | 200/500 | 49.5% | 31.7% | 34.5% | 64.7% | 100% | 50433 | 4.02¢ | 454s | | 14 | gpt-6.1-terra | 1571 ±51 | 500 | 48.4% | 35.7% | 33.2% | 68.3% | 99.8% | 1963 | 1.37¢ | 16s | | 15 | minimax-m3.1-flash | 1503 ±81 | 200/500 | 44% | 35.7% | 36% | 66.3% | 99.8% | 41055 | 0.13¢ | 467s | | 16 | muse-spark-1.3-contributor | 1493 ±51 | 500 | 44.4% | 24.5% | 42% | 57.8% | 100% | 17563 | 0.92¢ | 201s | | 17 | maia5-1500 | 1391 ±51 | 500 | 39.2% | 30.9% | 42% | 59.6% | 100% | - | - | - | | 18 | gpt-5.6-terra | 1384 ±81 | 200/500 | 38% | 29.8% | 43.5% | 57.4% | 99.6% | 2234 | 3.44¢ | 24s | | 19 | claude-sonnet-5.5 | 1325 ±81 | 200/500 | 35% | 27.7% | 47% | 55.2% | 99.8% | 1515 | 4.05¢ | 15s | | 20 | gpt-5.6-luna | 1317 ±51 | 500 | 35.4% | 24.8% | 48.6% | 51.8% | 100% | 3290 | 0.49¢ | 31s | | 21 | nemotron-3.5-super-vl | 1266 ±80 | 210/500 | 31.4% | 24.3% | 51.9% | 48% | 99.8% | 36283 | 0.13¢ | 502s | | 22 | claude-haiku-5.5 | 1239 ±51 | 500 | 31.4% | 25.1% | 51.4% | 51% | 100% | 2411 | 0.31¢ | 14s | | 23 | gpt-oss-120b | 1183 ±51 | 500 | 28.6% | 17.9% | 58.6% | 44% | 99.3% | 6504 | 0.44¢ | 155s | | 24 | gpt-6-luna-pro | 1163 ±84 | 190/500 | 27.4% | 21.7% | 56.8% | 45.1% | 99.8% | 7914 | 1.14¢ | 72s | | 25 | gpt-6-luna | 1103 ±52 | 500 | 24.6% | 23.1% | 58% | 44.8% | 99.9% | 3137 | 0.39¢ | 34s | | 26 | gemini-3.1-flash-lite-preview | 1083 ±52 | 500 | 23.6% | 23.6% | 58.4% | 48% | 97.9% | 93 | 0.04¢ | 1.6s | | 27 | claude-opus-4.8 | 1083 ±119 | 100/500 | 22% | 16.7% | 65% | 37% | 99.6% | 880 | 5.80¢ | 14s | | 28 | gpt-oss-20b | 1029 ±53 | 500 | 21% | 17% | 65.6% | 38% | 99.2% | 27860 | 1.01¢ | 155s | | 29 | qwen3.7-flash | 986 ±54 | 500 | 19% | 12.6% | 70.8% | 32.7% | 99.9% | 21700 | 0.73¢ | 205s | | 30 | gemini-3.5-flash-lite | 973 ±54 | 500 | 18.4% | 18.9% | 66.2% | 37.6% | 98.3% | 146 | 0.06¢ | 1.5s | | 31 | gpt-4.1 | 915 ±55 | 500 | 15.8% | 13.3% | 73% | 31.9% | 97.9% | 136 | 0.42¢ | 2.3s | | 32 | gemma-4-31b-it | 863 ±57 | 500 | 13.6% | 12.3% | 75.8% | 30.8% | 98.9% | 303 | <0.01¢ | 9.5s | | 33 | gemini-2.5-pro | 859 ±129 | 100/500 | 12% | 14.8% | 75% | 30.4% | 99.6% | 6681 | 16.20¢ | 59s | | 34 | gpt-4o | 843 ±58 | 500 | 12.8% | 10.8% | 77.8% | 28.9% | 96.9% | 128 | 0.50¢ | 1.8s | | 35 | llama-4-maverick | 843 ±58 | 500 | 12.8% | 10.6% | 78% | 29.3% | 99.3% | 452 | 0.11¢ | 10s | | 36 | gemma-4-26b-a4b-it | 833 ±58 | 500 | 12.4% | 10% | 78.8% | 27.7% | 94.7% | 1998 | 0.00¢ | 44s | | 37 | deepseek-v3.2 | 790 ±114 | 136/500 | 10.3% | 7.4% | 83.1% | 22.7% | 100% | 10716 | 0.88¢ | 250s | | 38 | north-mini-code | 780 ±61 | 500 | 10.4% | 8.9% | 81.6% | 24.5% | 99.2% | 37302 | 0.00¢ | 414s | | 39 | mistral-large-4.0 | 769 ±130 | 125/500 | 8% | 10.4% | 82.4% | 19.9% | 97.5% | 8287 | 4.08¢ | 124s | | 40 | nemotron-3.5-lightning | 723 ±75 | 380/500 | 8.2% | 8% | 84.5% | 22.2% | 99.2% | 24988 | 0.11¢ | 295s | | 41 | gpt-4-turbo ˟ | 721 ±65 | 500 | 8.4% | 9.2% | 83.2% | 22.2% | 98% | 286 | 2.83¢ | 8.0s | | 42 | kimi-k2-0905 | 709 ±66 | 500 | 8% | 7.6% | 85% | 21.9% | 99.3% | 599 | 0.39¢ | 11s | | 43 | gpt-5.4-nano | 689 ±67 | 500 | 7.4% | 7.3% | 85.8% | 20.8% | 98.4% | 171 | 0.06¢ | 2.3s | | 44 | gpt-4.1-mini | 675 ±68 | 500 | 7% | 7.3% | 86.2% | 20.5% | 98.2% | 101 | 0.07¢ | 1.5s | | 45 | gemini-2.5-flash | 638 ±72 | 500 | 6% | 7.2% | 87.2% | 19.1% | 94.8% | 1870 | 1.22¢ | 9.4s | | 46 | gpt-4o-mini | 614 ±75 | 500 | 5.4% | 2.3% | 92.4% | 12.7% | 99.3% | 62 | 0.02¢ | 1.3s | | 47 | gemini-2.5-flash-lite | 560 ±82 | 500 | 4.2% | 6.1% | 90% | 16.5% | 95.5% | 4445 | 0.42¢ | 11s | | 48 | llama-3.3-70b-instruct | 560 ±82 | 500 | 4.2% | 4.2% | 91.8% | 14.8% | 99.8% | 97 | 0.04¢ | 2.3s | | 49 | deepseek-v3 | 528 ±87 | 500 | 3.6% | 5.4% | 91.2% | 14.8% | 98.5% | 175 | 0.06¢ | 6.4s | | 50 | phi-4 | 528 ±87 | 500 | 3.6% | 2.5% | 94% | 11.8% | 86.8% | 156 | 0.01¢ | 2.8s | | 51 | gpt-3.5-turbo ˟ | 398 ±114 | 500 | 1.8% | 1.6% | 96.6% | 6.7% | 83.5% | 50 | 0.05¢ | 1.4s | | 52 | llama-4-scout | 377 ±119 | 500 | 1.6% | 2.6% | 95.8% | 8.8% | 99.9% | 132 | 0.02¢ | 6.1s | | 53 | ministral-3b-2512 | 301 ±144 | 500 | 1% | 1.8% | 97.2% | 5.1% | 96.8% | 191 | <0.01¢ | 1.4s | ## Trophy Room: Mixed Modes (min 10 games, excl. Humans) - Surgeon: highest average of accuracy, Reasoning legal % and Continuation legal % - Economist: highest (Elo - 400) per output token per move - Overthinker: most tokens per move per (Elo - 400), min 1000 tok/move - Glass Cannon: most decisive: (win% + loss%) - draw%, needs 25%+ wins and 20%+ losses - Magician: highest share of wins achieved while down material (min 10 wins) - Choker: highest share of losses suffered while ahead on material (min 10 losses) - Pacifist: highest draw rate (Elo 500+) - Rising Star: largest Elo gain over accuracy-based placement seed - Freefall: largest Elo drop below placement seed | Title | Rank | Model | Detail | Value | | --- | --- | --- | --- | --- | | Surgeon | 1 | gemini-3.8-flash | Acc 91.3% / Legal R:99.9% C:99.4% | 96.8% | | Surgeon | 2 | gemini-3.1-pro-preview | Acc 90% / Legal R:100% C:99.6% | 96.5% | | Surgeon | 3 | gemini-3-pro-preview ˟ | Acc 90.7% / Legal R:100% C:98.7% | 96.5% | | Economist | 1 | gemini-3-flash-preview | Elo 1583 ÷ 145 tok/move | 8.2 | | Economist | 2 | gpt-4.5-preview ˟ | Elo 1454 ÷ 133 tok/move | 7.9 | | Economist | 3 | gemini-3.5-flash-lite | Elo 1342 ÷ 141 tok/move | 6.7 | | Overthinker | 1 | olmo-3-7b-think | 15512 tok/move ÷ Elo 446 | 337.2 | | Overthinker | 2 | glm-4.7-flash | 25334 tok/move ÷ Elo 557 | 161.4 | | Overthinker | 3 | longcat-2.0 | 26931 tok/move ÷ Elo 703 | 88.9 | | Glass Cannon | 1 | minimax-m3.1-flash | 65%W / 0%D / 35%L | 100% | | Glass Cannon | 2 | claude-sonnet-5.5 | 53%W / 3%D / 44%L | 97% | | Glass Cannon | 3 | deepseek-v4-pro-0813 | 58%W / 4%D / 38%L | 96% | | Magician | 1 | gpt-4.1-mini | 7 of 25 wins while down material | 28% | | Magician | 2 | mistral-large-3-2512 | 2 of 11 wins while down material | 18.2% | | Magician | 3 | qwen3.5-35b-a3b | 2 of 13 wins while down material | 15.4% | | Choker | 1 | maia5-1500 | 4 of 17 losses while ahead on material | 23.5% | | Choker | 2 | gpt-4.1 | 4 of 17 losses while ahead on material | 23.5% | | Choker | 3 | gpt-5.6-terra | 5 of 22 losses while ahead on material | 22.7% | | Pacifist | 1 | internvl3-78b | 12 draws in 13 games | 92.3% | | Pacifist | 2 | ministral-8b | 18 draws in 21 games | 85.7% | | Pacifist | 3 | qwen3-30b-a3b-thinking-2507 | 12 draws in 14 games | 85.7% | | Rising Star | 1 | grok-build-0.1 | +221 R, -17 C | +208 | | Rising Star | 2 | gpt-4o | +32 R, +286 C | +172 | | Rising Star | 3 | gpt-3.5-turbo ˟ | -76 R, +181 C | +163 | | Freefall | 1 | grok-4.3 | -407 R, +11 C | -347 | | Freefall | 2 | codex-mini ˟ | -273 R | -273 | | Freefall | 3 | gpt-5-mini | -236 R, -130 C | -204 | ## Detailed Player Statistics: 5+ games, Reasoning (305 models) | # | Model | Elo | Cost | Games | W-D-L | Acc | Blunder | WR | Mat | Turns | Tok | Spd | Legal | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | gemini-3.1-pro-preview | 1931 ±110 | $2.33 | 51 | 42-5-4 | 90.9% | 2.2% | 87.3% | +8.2 | 41.3 | 4577 | 46s | 100% | | 2 | gemini-3.7-flash ˟ | 1851 ±155 | $0.08 | 22 | 16-3-3 | 91.6% | 2.5% | 79.5% | +8.8 | 40.8 | 631 | 5.5s | 100% | | 3 | gemini-3-pro-preview ˟ | 1850 ±135 | ~$1.93 | 45 | 38-3-4 | 90.7% | 2.4% | 87.8% | +12.2 | 38.4 | 4058 | 49s | 100% | | 4 | gemini-3.8-flash | 1849 ±157 | $0.24 | 20 | 14-2-4 | 91.4% | 1.7% | 75% | +8.2 | 48 | 1222 | 12s | 99.9% | | 5 | gpt-5-codex ˟ | 1777 ±199 | ~$9.17 | 23 | 19-1-3 | 89.9% | 2.8% | 84.8% | +10.3 | 40.5 | 22434 | 340s | 100% | | 6 | gemini-3.6-flash | 1753 ±134 | $0.42 | 25 | 14-5-6 | 87.3% | 3.4% | 66% | +5.9 | 42.7 | 1438 | 9.2s | 100% | | 7 | gpt-5.1-codex ˟ | 1743 ±135 | ~$7.19 | 22 | 13-4-5 | 89.6% | 3.6% | 68.2% | +3.9 | 47.5 | 15019 | 210s | 100% | | 8 | gpt-6-astra | 1734 ±117 | $1.11 | 25 | 14-5-6 | 84.8% | 3.1% | 66% | +1.6 | 53 | 568 | 13s | 100% | | 9 | claude-opus-5.5 | 1725 ±139 | $0.69 | 18 | 10-2-6 | 89.1% | 2.2% | 61.1% | +2.9 | 49.1 | 466 | 8.4s | 100% | | 10 | gemini-3.5-flash ˟ | 1721 ±107 | $0.77 | 37 | 21-8-8 | 86.7% | 3.2% | 67.6% | +6.5 | 48.8 | 1632 | 9.8s | 100% | | 11 | gpt-5.5 | 1668 ±112 | $5.09 | 31 | 15-7-9 | 85.3% | 3.7% | 59.7% | +6.4 | 44.5 | 3728 | 72s | 100% | | 12 | claude-fable-5 | 1611 ±110 | $4.30 | 42 | 21-6-15 | 83.5% | 4% | 57.1% | +2.4 | 43.1 | 1766 | 29s | 99.9% | | 13 | gemini-4-argon | 1597 ±136 | $0.16 | 20 | 13-1-6 | 83.3% | 3.6% | 67.5% | +5.5 | 43 | 235 | 6.2s | 100% | | 14 | gpt-5.6-sol | 1597 ±89 | $2.09 | 44 | 23-12-9 | 81.5% | 4.6% | 65.9% | +3.6 | 47.8 | 1656 | 36s | 100% | | 15 | grok-4 ˟ | 1596 ±154 | ~$14.05 | 28 | 15-4-9 | 87.6% | 3.3% | 60.7% | +8 | 40.1 | 23175 | 689s | 100% | | 16 | maia5-1500 | 1569 ±123 | - | 25 | 14-3-8 | 82.7% | 3.6% | 62% | +7.1 | 36.4 | - | - | 100% | | 17 | gpt-5 | 1549 ±134 | $3.59 | 30 | 21-2-7 | 82.8% | 4% | 73.3% | +7 | 38.9 | 9184 | 163s | 100% | | 18 | deepseek-v4-flash-0731 | 1545 ±127 | $0.45 | 27 | 15-2-10 | 84.9% | 5% | 59.3% | +1.7 | 49.5 | 34070 | 333s | 100% | | 19 | o3 | 1544 ±96 | $2.78 | 53 | 31-10-12 | 80.9% | 4.1% | 67.9% | +4.7 | 47.4 | 7109 | 97s | 100% | | 20 | qwen3.8-max | 1540 ±123 | ~$8.65 | 24 | 12-5-7 | 80.4% | 4% | 60.4% | +3.7 | 49.7 | 28729 | 506s | 100% | | 21 | kimi-k3 | 1530 ±132 | ~$6.30 | 22 | 14-4-4 | 82.5% | 3.5% | 72.7% | +5.3 | 44.2 | 9335 | 295s | 99.9% | | 22 | gpt-5.1 | 1527 ±133 | ~$2.62 | 23 | 11-4-8 | 84% | 4.1% | 56.5% | 0 | 41.5 | 6202 | 120s | 100% | | 23 | hy3 | 1501 ±111 | $0.17 | 28 | 13-8-7 | 81.8% | 5.9% | 60.7% | +4.6 | 39.4 | 7608 | 112s | 100% | | 24 | grok-4.20-reasoning | 1478 ±112 | $0.99 | 33 | 15-6-12 | 81.4% | 4.6% | 54.5% | +4.2 | 42 | 3854 | 28s | 100% | | 25 | gpt-6.1-sol | 1475 ±126 | $0.19 | 21 | 10-4-7 | 83.6% | 3.4% | 57.1% | -1.1 | 50.6 | 579 | 16s | 100% | | 26 | deepseek-v4-pro-0813 | 1464 ±160 | $3.61 | 15 | 10-1-4 | 77.4% | 4.7% | 70% | +7.7 | 48.1 | 36510 | 490s | 100% | | 27 | gemini-3-flash-preview | 1456 ±85 | $0.02 | 58 | 26-19-13 | 82.5% | 3.7% | 61.2% | +3.3 | 41.9 | 99 | 2.6s | 99.9% | | 28 | gpt-6.1-terra | 1417 ±133 | $0.12 | 19 | 12-3-4 | 78.5% | 5.8% | 71.1% | +4.1 | 41.6 | 874 | 9.7s | 99.9% | | 29 | gemini-3.1-flash-lite-preview | 1397 ±99 | $0.007 | 47 | 19-15-13 | 74.6% | 6.3% | 56.4% | +1.3 | 40.5 | 97 | 1.8s | 98.9% | | 30 | grok-4.3 | 1393 ±137 | $0.37 | 28 | 9-4-15 | 80.3% | 5.9% | 39.3% | -4 | 35.8 | 3900 | 52s | 100% | | 31 | deepseek-v4.1-flash-1017 | 1379 ±150 | $0.61 | 15 | 8-0-7 | 80.5% | 5.5% | 53.3% | +1.3 | 40.2 | 26162 | 132s | 100% | | 32 | grok-4.5 | 1368 ±118 | $1.06 | 27 | 13-4-10 | 76.2% | 5.5% | 55.6% | -1.6 | 39.7 | 4267 | 58s | 100% | | 33 | kimi-k2.6 | 1363 ±130 | ~$2.39 | 27 | 13-3-11 | 75.6% | 6% | 53.7% | +1.9 | 30 | 20659 | 355s | 100% | | 34 | grok-build-0.1 | 1356 ±104 | $0.85 | 28 | 14-9-5 | 79% | 4.7% | 66.1% | +12.2 | 37.1 | 11170 | 88s | 100% | | 35 | gpt-5.1-codex-max ˟ | 1354 ±122 | ~$3.42 | 20 | 5-7-8 | 80.1% | 5% | 42.5% | -1.6 | 45.9 | 7349 | 99s | 100% | | 36 | deepseek-v4.1-flash | 1351 ±140 | $0.81 | 18 | 10-1-7 | 77.3% | 5% | 58.3% | +2.1 | 42.1 | 29436 | 133s | 100% | | 37 | claude-sonnet-5.5 | 1349 ±135 | $0.36 | 20 | 14-1-5 | 78.8% | 4.2% | 72.5% | +6.3 | 38.3 | 725 | 8.3s | 99.9% | | 38 | gpt-5.6-luna | 1344 ±101 | $0.39 | 33 | 12-8-13 | 81% | 4.9% | 48.5% | -1.9 | 45.8 | 1635 | 17s | 100% | | 39 | minimax-m3.1-flash | 1329 ±148 | $0.49 | 15 | 10-0-5 | 78.9% | 6.2% | 66.7% | +0.9 | 33.4 | 26972 | 285s | 100% | | 40 | claude-fable-5.1 | 1324 ±126 | $4.19 | 19 | 4-5-10 | 77.3% | 4% | 34.2% | -1.6 | 50.2 | 1431 | 24s | 100% | | 41 | gpt-6-sol | 1311 ±114 | $0.65 | 19 | 5-8-6 | 74.3% | 6% | 47.4% | -0.1 | 53.3 | 1235 | 20s | 100% | | 42 | gpt-5.2-codex ˟ | 1303 ±127 | ~$1.36 | 23 | 7-6-10 | 76.4% | 5.3% | 43.5% | -0.8 | 39.8 | 2507 | 39s | 100% | | 43 | claude-sonnet-5 | 1302 ±102 | $1.42 | 29 | 10-10-9 | 78.2% | 5.7% | 51.7% | -0.8 | 42.4 | 3116 | 38s | 99.9% | | 44 | claude-haiku-5.5 | 1291 ±140 | $0.03 | 17 | 7-2-8 | 74.5% | 6.9% | 47.1% | +1 | 36.7 | 1258 | 7.3s | 100% | | 45 | gpt-5.6-terra | 1284 ±95 | $0.73 | 33 | 9-12-12 | 74.6% | 6.1% | 45.5% | +1.9 | 47.7 | 1148 | 17s | 99.9% | | 46 | muse-spark-1.3 | 1268 ±140 | $1.72 | 15 | 7-2-6 | 76.1% | 5.1% | 53.3% | +2 | 51.1 | 7729 | 93s | 100% | | 47 | muse-spark-1.3-contributor | 1257 ±129 | $0.08 | 18 | 8-3-7 | 76.8% | 5.2% | 52.8% | +1.5 | 53.2 | 7334 | 81s | 100% | | 48 | muse-spark-1.2 | 1252 ±111 | ~$1.35 | 25 | 13-6-6 | 77.3% | 5.6% | 64% | +2.8 | 49.2 | 6293 | 40s | 100% | | 49 | gpt-5.3-codex | 1242 ±118 | ~$1.02 | 21 | 8-7-6 | 77.1% | 5.3% | 54.8% | +3.9 | 38 | 1836 | 36s | 100% | | 50 | grok-4.6 | 1242 ±127 | $1.22 | 19 | 8-4-7 | 75.9% | 5.4% | 52.6% | +3.2 | 45.4 | 4235 | 81s | 100% | | 51 | kimi-k2.7-code | 1224 ±118 | ~$1.71 | 23 | 7-7-9 | 73.9% | 5.3% | 45.7% | -3.7 | 37.3 | 11590 | 197s | 99.8% | | 52 | gemini-3.5-flash-lite | 1220 ±122 | $0.02 | 25 | 7-5-13 | 73.2% | 6.4% | 38% | -3 | 57.4 | 88 | 2.0s | 98.4% | | 53 | gpt-5.2 | 1213 ±112 | ~$2.61 | 26 | 8-9-9 | 76.3% | 4.6% | 48.1% | +1.8 | 48.2 | 3781 | 79s | 100% | | 54 | glm-5.3-flash | 1206 ±151 | $0.44 | 16 | 6-1-9 | 80.7% | 5.1% | 40.6% | -2.8 | 42 | 29666 | 390s | 99.9% | | 55 | qwen3.7-max | 1191 ±104 | ~$1.22 | 30 | 11-11-8 | 72.2% | 7.2% | 55% | +0.9 | 42.2 | 5132 | 84s | 100% | | 56 | qwen3.8-flash | 1190 ±144 | $0.76 | 13 | 3-3-7 | 76.9% | 5.8% | 34.6% | +0.5 | 40.5 | 39662 | 363s | 99.6% | | 57 | claude-opus-4.7 | 1184 ±99 | ~$0.47 | 38 | 14-13-11 | 69% | 6.2% | 53.9% | -0.7 | 37.8 | 272 | 6.4s | 99.7% | | 58 | laguna-s-2.1 | 1183 ±136 | $0.18 | 16 | 3-5-8 | 79.3% | 4.1% | 34.4% | -5.9 | 45.5 | 25307 | 210s | 99.9% | | 59 | grok-4.1-fast-reasoning ˟ | 1182 ±121 | ~$0.09 | 31 | 14-5-12 | 74.3% | 6.4% | 53.2% | +5.1 | 30.1 | 6421 | 121s | 100% | | 60 | step-3.5-flash | 1181 ±125 | ~$0.47 | 28 | 14-6-8 | 72.9% | 6.9% | 60.7% | +5.5 | 35.8 | 43256 | 156s | 100% | | 61 | claude-opus-5 | 1165 ±122 | $1.55 | 25 | 10-4-11 | 75.3% | 5.8% | 48% | +2.1 | 37.8 | 1418 | 23s | 100% | | 62 | muse-glimmer-30b | 1157 ±127 | $0.71 | 22 | 11-5-6 | 75% | 6.5% | 61.4% | -1.6 | 44.3 | 10748 | 151s | 100% | | 63 | qwen3.8-27b | 1145 ±161 | $2.72 | 9 | 3-2-4 | 75.4% | 5% | 44.4% | -2 | 46.7 | 23713 | 279s | 99.8% | | 64 | grok-4-fast-reasoning ˟ | 1145 ±110 | ~$0.09 | 32 | 11-11-10 | 73.2% | 6.5% | 51.6% | +5.8 | 36.3 | 5425 | 44s | 100% | | 65 | gpt-6-luna | 1122 ±131 | $0.03 | 17 | 1-4-12 | 77.7% | 6.2% | 17.6% | -9.4 | 42.9 | 1189 | 18s | 99.9% | | 66 | claude-opus-4.8 | 1121 ±116 | ~$0.41 | 27 | 9-7-11 | 76.4% | 5.9% | 46.3% | -0.1 | 34 | 262 | 5.4s | 99.7% | | 67 | gpt-5-nano | 1116 ±112 | ~$0.13 | 35 | 14-10-11 | 73.9% | 7.3% | 54.3% | +2.5 | 42 | 7799 | 69s | 100% | | 68 | grok-4.7 | 1113 ±143 | $1.36 | 16 | 7-2-7 | 69.7% | 6.6% | 50% | +0.2 | 40.6 | 6425 | 98s | 100% | | 69 | gpt-5-mini | 1108 ±108 | ~$0.24 | 35 | 11-10-14 | 73.6% | 7.6% | 45.7% | +1.4 | 40.1 | 2894 | 55s | 100% | | 70 | codex-mini ˟ | 1108 ±111 | ~$1.37 | 35 | 13-13-9 | 72.4% | 5.5% | 55.7% | +1.9 | 43.6 | 5080 | 41s | 100% | | 71 | muse-spark-1.1 | 1084 ±127 | ~$0.83 | 24 | 9-3-12 | 75% | 6.6% | 43.8% | -1.4 | 42.7 | 4415 | 27s | 100% | | 72 | muse-spark-1.2-contributor | 1072 ±123 | $0.05 | 22 | 6-4-12 | 73.2% | 7.2% | 36.4% | -2.8 | 44.3 | 5717 | 48s | 100% | | 73 | deepseek-v3.2-speciale | 1069 ±108 | ~$0.60 | 26 | 10-10-6 | 71.3% | 6% | 57.7% | +1 | 53.3 | 22410 | 553s | 100% | | 74 | nemotron-3.5-super-vl | 1060 ±137 | $0.18 | 15 | 3-4-8 | 74.6% | 7.1% | 33.3% | -2.5 | 44.2 | 12223 | 184s | 100% | | 75 | o4-mini ˟ | 1034 ±104 | ~$0.83 | 37 | 14-15-8 | 72.7% | 6.9% | 58.1% | +1.7 | 45.2 | 3993 | 62s | 100% | | 76 | gpt-5.3-chat ˟ | 1023 ±116 | ~$0.42 | 20 | 9-7-4 | 67.4% | 9% | 62.5% | +2.4 | 40.8 | 637 | 9.5s | 99.6% | | 77 | qwen3.6-plus | 1008 ±100 | $0.31 | 23 | 9-12-2 | 69% | 6.7% | 65.2% | +3.6 | 45.5 | 3371 | 62s | 100% | | 78 | nemotron-3-super-120b-a12b | 1000 ±140 | ~$1.66 | 12 | 5-4-3 | 70.5% | 8.4% | 58.3% | +1.1 | 44.1 | 41215 | 614s | 98.9% | | 79 | gpt-4.5-preview ˟ | 992 ±123 | ~$2.72 | 15 | 6-8-1 | 72.8% | 6.7% | 66.7% | +7.1 | 43.3 | 86 | 4.5s | 100% | | 80 | glm-5.2 | 979 ±114 | ~$0.72 | 20 | 6-8-6 | 74.4% | 6.6% | 50% | -0.2 | 44.9 | 3639 | 71s | 99.9% | | 81 | gemma-4-26b-a4b-it | 972 ±99 | $0.007 | 27 | 9-16-2 | 64.8% | 8.4% | 63% | +7.3 | 46.6 | 166 | 6.1s | 99.4% | | 82 | qwen3.5-35b-a3b | 971 ±98 | ~$0.42 | 28 | 12-11-5 | 70.1% | 9% | 62.5% | +3.1 | 37.8 | 8928 | 67s | 99.9% | | 83 | kimi-k2.5 | 960 ±91 | ~$0.75 | 35 | 7-16-12 | 67% | 9% | 42.9% | -3.6 | 40.4 | 6769 | 139s | 99.8% | | 84 | qwen3.5-flash | 960 ±109 | ~$0.15 | 20 | 6-11-3 | 65.1% | 8.8% | 57.5% | +2.2 | 46.6 | 9391 | 63s | 100% | | 85 | hy3-preview | 956 ±125 | ~$0.29 | 16 | 3-8-5 | 70.3% | 8% | 43.8% | -3.1 | 51.1 | 9217 | 110s | 99.5% | | 86 | gpt-5.1-codex-mini ˟ | 952 ±130 | ~$0.51 | 22 | 7-5-10 | 70.4% | 7.4% | 43.2% | -1.4 | 39.1 | 4089 | 46s | 100% | | 87 | gemini-2.5-pro | 951 ±83 | ~$0.77 | 49 | 18-19-12 | 68.5% | 7.6% | 56.1% | +1.3 | 42.5 | 1886 | 27s | 99.9% | | 88 | qwen3.5-122b-a10b | 942 ±103 | ~$0.55 | 24 | 7-10-7 | 66.6% | 8.6% | 50% | +0.5 | 43 | 5288 | 51s | 99.9% | | 89 | qwen3.7-flash | 930 ±121 | $0.02 | 19 | 1-8-10 | 68% | 8.2% | 26.3% | -8.2 | 48.3 | 3345 | 27s | 100% | | 90 | gpt-oss-120b | 921 ±93 | ~$0.12 | 39 | 16-14-9 | 70% | 7.8% | 59% | +7.1 | 43.6 | 4500 | 33s | 99.8% | | 91 | qwen3.6-35b-a3b | 919 ±105 | ~$0.20 | 20 | 6-9-5 | 63.3% | 10.3% | 52.5% | -1.3 | 39.8 | 3669 | 33s | 99.9% | | 92 | qwen3.6-flash | 905 ±149 | $0.13 | 16 | 1-3-12 | 68.9% | 9.8% | 15.6% | -10.3 | 35.8 | 3196 | 28s | 100% | | 93 | mimo-v2.5-pro | 904 ±114 | ~$0.91 | 18 | 4-13-1 | 59.8% | 11.3% | 58.3% | +1.5 | 51.2 | 5978 | 97s | 100% | | 94 | grok-code-fast-1 ˟ | 892 ±104 | ~$0.35 | 25 | 7-12-6 | 61.3% | 9% | 52% | +1.2 | 50 | 4598 | 32s | 99.8% | | 95 | gpt-5.4 | 883 ±135 | ~$0.10 | 26 | 3-4-19 | 71.6% | 8.9% | 19.2% | -9.2 | 28.9 | 117 | 3.2s | 99.5% | | 96 | deepseek-v4-pro | 881 ±119 | ~$0.88 | 21 | 4-8-9 | 63.8% | 10.2% | 38.1% | -6.7 | 41.5 | 9578 | 190s | 99.9% | | 97 | claude-opus-4.5 | 878 ±93 | ~$0.51 | 31 | 4-20-7 | 60% | 9.4% | 45.2% | -3.4 | 45.3 | 277 | 8.3s | 99.9% | | 98 | mimo-v2-omni | 876 ±105 | ~$0.42 | 21 | 6-11-4 | 62% | 10.7% | 54.8% | +2.5 | 42.5 | 4835 | 37s | 99.8% | | 99 | deepseek-v4-flash | 874 ±106 | ~$0.08 | 22 | 6-10-6 | 63.7% | 7.3% | 50% | +1.1 | 45.7 | 5887 | 81s | 99.9% | | 100 | gemma-4-31b-it | 866 ±94 | ~$0.006 | 31 | 8-12-11 | 64.9% | 9.4% | 45.2% | +1.9 | 36.4 | 149 | 16s | 99.7% | | 101 | qwen3.6-27b | 865 ±110 | ~$1.13 | 17 | 4-8-5 | 67.5% | 9.3% | 47.1% | -0.6 | 40.6 | 10588 | 200s | 100% | | 102 | qwen3.5-397b-a17b | 865 ±101 | ~$0.43 | 22 | 6-12-4 | 64.4% | 8.8% | 54.5% | +1.3 | 46.3 | 2623 | 57s | 100% | | 103 | qwen3.5-27b | 853 ±101 | ~$0.76 | 21 | 6-11-4 | 63.2% | 10% | 54.8% | +3.1 | 43 | 7765 | 97s | 100% | | 104 | gpt-oss-20b | 850 ±89 | ~$0.15 | 33 | 12-17-4 | 62% | 8.9% | 62.1% | +7.5 | 52.4 | 18071 | 51s | 99.7% | | 105 | nemotron-3-nano-30b-a3b | 848 ±89 | ~$0.19 | 34 | 11-16-7 | 69.7% | 9% | 55.9% | +2.4 | 49 | 18692 | 55s | 99.5% | | 106 | seed-2.0-lite | 847 ±105 | ~$0.20 | 21 | 5-11-5 | 67.3% | 7.6% | 50% | +1 | 50.5 | 1917 | 55s | 100% | | 107 | gpt-5-chat ˟ | 847 ±93 | ~$0.09 | 30 | 8-15-7 | 62.2% | 8.7% | 51.7% | -3 | 50.2 | 102 | 2.6s | 99.8% | | 108 | claude-opus-4.6 | 845 ±82 | ~$0.73 | 38 | 6-22-10 | 61.7% | 10.9% | 44.7% | -3.4 | 44.2 | 484 | 13s | 99.9% | | 109 | qwen3.5-plus-02-15 | 839 ±105 | ~$0.12 | 20 | 5-12-3 | 60.7% | 11.6% | 55% | -0.3 | 47.3 | 1049 | 20s | 99.2% | | 110 | gpt-5.1-chat ˟ | 837 ±111 | ~$0.10 | 22 | 4-9-9 | 60.9% | 7.1% | 38.6% | -3.9 | 38.3 | 175 | 3.2s | 100% | | 111 | gpt-5.2-chat ˟ | 835 ±123 | ~$0.31 | 23 | 6-6-11 | 65.7% | 9.1% | 39.1% | -2.7 | 32 | 608 | 11s | 99.7% | | 112 | seed-2.0-mini | 833 ±107 | ~$0.20 | 18 | 6-9-3 | 61.1% | 10.2% | 58.3% | +4.9 | 43.9 | 11018 | 284s | 100% | | 113 | mimo-v2.5 | 828 ±115 | ~$0.57 | 16 | 3-12-1 | 60.8% | 9% | 56.3% | +1.3 | 56.8 | 5210 | 73s | 100% | | 114 | step-3.7-flash | 827 ±147 | $0.93 | 12 | 2-4-6 | 62% | 13.4% | 33.3% | -5.5 | 36.4 | 21945 | 135s | 99.8% | | 115 | gpt-4o | 821 ±80 | ~$0.15 | 41 | 8-24-9 | 62.6% | 10.3% | 48.8% | -1.1 | 52.1 | 112 | 3.1s | 99.7% | | 116 | nemotron-3-ultra-550b-a55b | 821 ±147 | ~$1.08 | 11 | 4-3-4 | 61% | 9.3% | 50% | -1.9 | 43.3 | 8167 | 146s | 98.8% | | 117 | minimax-m3 | 821 ±147 | $0.90 | 12 | 5-3-4 | 58.9% | 7.3% | 54.2% | +4.8 | 35.5 | 20963 | 358s | 99.8% | | 118 | seed-oss-36b-instruct | 818 ±125 | ~$0.26 | 13 | 5-6-2 | 62.1% | 10.2% | 61.5% | -0.6 | 47.8 | 6914 | 41s | 100% | | 119 | gpt-4.1 | 817 ±82 | ~$0.12 | 40 | 11-24-5 | 60.7% | 9.2% | 57.5% | +1.8 | 53.6 | 110 | 2.8s | 100% | | 120 | qwen3.7-plus | 807 ±141 | ~$0.46 | 13 | 3-4-6 | 63.6% | 8.5% | 38.5% | -2.2 | 39.2 | 7593 | 142s | 100% | | 121 | o1 ˟ | 807 ±144 | ~$11.23 | 11 | 1-6-4 | 60.5% | 7.4% | 36.4% | -3.7 | 48 | 3726 | 30s | 100% | | 122 | glm-5 | 801 ±100 | ~$0.78 | 24 | 3-17-4 | 61.5% | 9% | 47.9% | -1.6 | 54.8 | 4365 | 114s | 100% | | 123 | qwen3.5-9b | 801 ±104 | ~$0.16 | 21 | 6-13-2 | 58.5% | 10% | 59.5% | +5.4 | 51.5 | 19819 | 87s | 99.5% | | 124 | chatgpt-4o-latest ˟ | 799 ±119 | ~$0.27 | 17 | 2-10-5 | 57.6% | 11.4% | 41.2% | -3.2 | 49.1 | 121 | 1.9s | 99.4% | | 125 | longcat-2.0 | 791 ±130 | ~$0.77 | 14 | 3-5-6 | 60.6% | 10.8% | 39.3% | -2.2 | 44.8 | 14179 | 121s | 99.7% | | 126 | seed-1.6 | 790 ±102 | ~$0.11 | 23 | 5-10-8 | 62.7% | 9.5% | 43.5% | +0.8 | 42.3 | 1184 | 29s | 100% | | 127 | glm-5.1 | 787 ±105 | ~$1.07 | 20 | 2-12-6 | 61.2% | 10.6% | 40% | -4.1 | 45.2 | 5404 | 114s | 100% | | 128 | qwen3-next-80b-a3b-thinking | 786 ±104 | ~$0.75 | 20 | 7-12-1 | 50.7% | 12.8% | 65% | +3.1 | 54.4 | 11414 | 59s | 99.1% | | 129 | claude-sonnet-4.6 | 767 ±108 | $0.45 | 26 | 3-12-11 | 60.2% | 10.7% | 34.6% | -6.6 | 38.8 | 607 | 13s | 99.5% | | 130 | o1-mini ˟ | 766 ±97 | ~$0.40 | 24 | 8-14-2 | 55.7% | 14.1% | 62.5% | +2.3 | 54.1 | 1473 | 18s | 100% | | 131 | grok-3-mini ˟ | 764 ±81 | ~$0.09 | 40 | 11-18-11 | 58% | 12.1% | 50% | +0.2 | 43.3 | 1631 | 16s | 100% | | 132 | mimo-v2-pro ˟ | 756 ±106 | ~$1.08 | 18 | 4-13-1 | 61.6% | 10.3% | 58.3% | +2.4 | 59.8 | 5886 | 88s | 100% | | 133 | north-mini-code | 756 ±103 | - | 22 | 5-13-4 | 54.5% | 13.3% | 52.3% | +0.1 | 45.7 | 14933 | 143s | 99.8% | | 134 | grok-4-fast-non-reasoning ˟ | 754 ±98 | ~$0.01 | 25 | 4-17-4 | 60.6% | 9.9% | 50% | +1.4 | 54.5 | 149 | 1.8s | 97.4% | | 135 | gemini-2.5-flash | 754 ±86 | ~$0.06 | 35 | 7-19-9 | 59.8% | 9.7% | 47.1% | -1.4 | 61 | 232 | 6.2s | 98.5% | | 136 | ling-3.0-flash | 752 ±127 | $0.02 | 12 | 2-7-3 | 62.4% | 13.5% | 45.8% | -1.4 | 61.8 | 2563 | 12s | 94% | | 137 | deepseek-v3.2 | 748 ±96 | ~$0.01 | 24 | 6-15-3 | 51.8% | 12.6% | 56.3% | -0.1 | 56 | 188 | 13s | 100% | | 138 | nemotron-3.5-lightning | 746 ±135 | $0.06 | 16 | 0-7-9 | 62.4% | 11.8% | 21.9% | -7.9 | 51.8 | 7832 | 79s | 99.9% | | 139 | gpt-5.4-nano | 746 ±104 | ~$0.02 | 20 | 2-15-3 | 58.2% | 9.1% | 47.5% | +0.1 | 67.9 | 137 | 2.2s | 98.3% | | 140 | qwen3-8b | 743 ±104 | ~$0.11 | 20 | 5-15-0 | 58.1% | 9% | 62.5% | +7.9 | 60.4 | 9047 | 153s | 98.9% | | 141 | command-a | 740 ±104 | ~$0.15 | 21 | 3-13-5 | 62.8% | 11.4% | 45.2% | +4.3 | 49.6 | 116 | 4.7s | 98.6% | | 142 | kimi-k2 | 740 ±85 | ~$0.04 | 35 | 6-21-8 | 58.1% | 12.1% | 47.1% | -1 | 56.3 | 148 | 7.7s | 96.8% | | 143 | qwen3-14b | 736 ±101 | ~$0.11 | 20 | 4-14-2 | 54.7% | 13.3% | 55% | +1.5 | 65.1 | 6358 | 107s | 99.8% | | 144 | claude-haiku-4.5 | 735 ±95 | $0.11 | 28 | 6-14-8 | 55.5% | 12.3% | 46.4% | -1.3 | 48.5 | 249 | 3.6s | 98.6% | | 145 | kimi-k2-0905 | 732 ±89 | ~$0.04 | 35 | 8-14-13 | 53.2% | 11.2% | 42.9% | -3.5 | 46.6 | 147 | 6.8s | 98.4% | | 146 | minimax-m2 | 721 ±102 | ~$0.48 | 24 | 3-13-8 | 59.1% | 10.6% | 39.6% | -4.3 | 45.3 | 9828 | 117s | 98.9% | | 147 | gpt-5.4-mini | 719 ±106 | ~$0.05 | 20 | 3-11-6 | 56.8% | 11.8% | 42.5% | -2.9 | 49.3 | 95 | 1.8s | 99.6% | | 148 | o3-mini ˟ | 717 ±109 | ~$0.55 | 19 | 3-11-5 | 61.3% | 10.3% | 44.7% | -1.6 | 44.9 | 2648 | 38s | 100% | | 149 | gpt-4.1-mini | 717 ±90 | ~$0.04 | 29 | 7-16-6 | 53.6% | 13.9% | 51.7% | -3.3 | 66.8 | 113 | 5.0s | 99.5% | | 150 | kimi-k2-thinking | 713 ±109 | ~$1.43 | 22 | 2-13-7 | 58.8% | 10.7% | 38.6% | -3.2 | 47.7 | 8423 | 259s | 100% | | 151 | laguna-xs-2.1 | 711 ±122 | ~$0.08 | 16 | 1-7-8 | 52.5% | 11.7% | 28.1% | -5.8 | 49.1 | 7369 | 76s | 96.7% | | 152 | deepseek-r1 | 711 ±124 | ~$0.45 | 14 | 6-6-2 | 52.4% | 12.9% | 64.3% | +1.4 | 40.7 | 4144 | 104s | 100% | | 153 | qwen3-coder-next | 707 ±116 | ~$0.18 | 15 | 4-9-2 | 49.9% | 12.1% | 56.7% | +0.7 | 64.7 | 2384 | 11s | 95.9% | | 154 | claude-opus-4 ˟ | 704 ±98 | ~$1.51 | 27 | 1-19-7 | 59.4% | 10.3% | 38.9% | -3.6 | 55.5 | 183 | 9.4s | 99.2% | | 155 | qwen2.5-72b-instruct | 704 ±79 | ~$0.01 | 38 | 8-24-6 | 59.1% | 9.3% | 52.6% | +3.6 | 70.1 | 92 | 7.2s | 95.4% | | 156 | longcat-flash-chat | 701 ±99 | ~$0.02 | 22 | 7-12-3 | 47.4% | 13.2% | 59.1% | -0.5 | 52.9 | 205 | 4.5s | 98.7% | | 157 | internvl3-78b | 696 ±127 | ~$0.009 | 11 | 1-10-0 | 56.3% | 12.3% | 54.5% | +5 | 77 | 113 | 4.0s | 96.6% | | 158 | qwen3-plus-07-28 | 695 ±102 | ~$0.04 | 21 | 2-17-2 | 59.6% | 10.9% | 50% | -1.7 | 62.4 | 255 | 4.9s | 98.9% | | 159 | claude-opus-4.1 | 694 ±97 | ~$1.02 | 31 | 3-13-15 | 56.7% | 11.9% | 30.6% | -4.8 | 38.4 | 182 | 9.6s | 98.9% | | 160 | qwen3-max | 694 ±102 | ~$0.16 | 23 | 4-12-7 | 56.5% | 12.3% | 43.5% | -2.6 | 57.6 | 320 | 12s | 99.9% | | 161 | mistral-large-2-2411 | 694 ±78 | ~$0.17 | 37 | 9-24-4 | 49.2% | 15.4% | 56.8% | +0.6 | 63.8 | 105 | 12s | 88% | | 162 | llama-3.3-70b-instruct | 688 ±66 | ~$0.01 | 56 | 14-33-9 | 50.7% | 15.9% | 54.5% | +1.1 | 57.5 | 154 | 9.5s | 99.2% | | 163 | ling-2.6-1t | 685 ±144 | ~$0.007 | 14 | 2-4-8 | 53.8% | 15.1% | 28.6% | -9.1 | 35 | 210 | 3.8s | 99.6% | | 164 | glm-4.6v | 681 ±108 | ~$0.10 | 18 | 3-12-3 | 57% | 11.3% | 50% | -2.4 | 66.1 | 1550 | 28s | 99.7% | | 165 | mistral-large-3-2512 | 678 ±109 | ~$0.04 | 20 | 7-8-5 | 50.9% | 16.3% | 55% | -4.7 | 56.3 | 266 | 12s | 99.6% | | 166 | qwen3-32b | 672 ±94 | ~$0.12 | 29 | 8-12-9 | 57.2% | 11.1% | 48.3% | -0.3 | 48.9 | 5620 | 108s | 99.8% | | 167 | claude-sonnet-4.5 | 671 ±91 | ~$0.43 | 32 | 7-14-11 | 54.1% | 12.1% | 43.8% | -2.1 | 46.7 | 423 | 10s | 98.9% | | 168 | glm-4.5 | 671 ±97 | ~$0.34 | 22 | 5-13-4 | 47.4% | 14.9% | 52.3% | +0.3 | 60.8 | 2615 | 33s | 98.1% | | 169 | qwen2.5-max ˟ | 667 ±96 | ~$0.07 | 23 | 4-13-6 | 52.6% | 14.8% | 45.7% | -2 | 50.3 | 107 | 11s | 97.8% | | 170 | qwen3-235b-a22b-thinking-2507 | 666 ±107 | ~$0.79 | 19 | 1-15-3 | 49.7% | 13.3% | 44.7% | -4.4 | 60.5 | 7778 | 137s | 99.7% | | 171 | seed-1.6-flash | 665 ±103 | ~$0.15 | 22 | 2-14-6 | 52.6% | 14.8% | 40.9% | -4.2 | 72.7 | 6578 | 42s | 99.1% | | 172 | grok-4.20-non-reasoning | 664 ±125 | ~$0.09 | 16 | 1-8-7 | 54.3% | 9% | 31.3% | -4.5 | 48.1 | 97 | 1.2s | 99.5% | | 173 | deepseek-r1-0528 | 662 ±115 | ~$0.96 | 16 | 1-12-3 | 57.4% | 10.4% | 43.8% | -2.4 | 56.8 | 6770 | 188s | 99.6% | | 174 | phi-4 | 662 ±116 | ~$0.007 | 16 | 6-7-3 | 45.9% | 20.3% | 59.4% | +5.2 | 71.1 | 153 | 7.0s | 79.3% | | 175 | gemma-2-27b-it | 661 ±100 | ~$0.04 | 22 | 3-14-5 | 52.4% | 17.1% | 45.5% | -1.3 | 62.9 | 59 | 2.8s | 92% | | 176 | devstral-2512 | 660 ±116 | ~$0.03 | 18 | 4-7-7 | 56.5% | 10.9% | 41.7% | -2.4 | 51.9 | 143 | 4.4s | 98.1% | | 177 | deepseek-v3.2-exp | 660 ±107 | ~$0.01 | 18 | 4-9-5 | 49.6% | 13.2% | 47.2% | -1.2 | 45.1 | 291 | 9.5s | 99.2% | | 178 | grok-2-latest ˟ | 659 ±111 | ~$0.22 | 16 | 2-14-0 | 50% | 11.4% | 56.3% | +6.4 | 73.4 | 136 | 4.4s | 98.3% | | 179 | gemini-2.5-flash-lite | 655 ±88 | ~$0.02 | 32 | 7-16-9 | 57.4% | 13.4% | 46.9% | +2.2 | 50.2 | 362 | 2.0s | 85.4% | | 180 | minimax-m1 | 653 ±127 | ~$0.87 | 15 | 2-6-7 | 57.8% | 10.7% | 33.3% | -4.9 | 52 | 8340 | 518s | 99.7% | | 181 | claude-3.7-sonnet ˟ | 653 ±89 | ~$0.29 | 27 | 4-19-4 | 47% | 15.2% | 50% | +0.1 | 53.7 | 181 | 6.4s | 100% | | 182 | ministral-14b-2512 | 650 ±107 | $0.02 | 18 | 3-10-5 | 57.6% | 15.6% | 44.4% | -0.8 | 61.9 | 368 | 4.2s | 88.8% | | 183 | olmo-3-32b-think | 650 ±117 | ~$0.29 | 15 | 6-8-1 | 44.6% | 15.1% | 66.7% | +1.5 | 57.7 | 12632 | 210s | 99.9% | | 184 | gpt-4o-mini | 649 ±98 | ~$0.009 | 23 | 4-12-7 | 52.8% | 15.6% | 43.5% | -2.3 | 56.1 | 75 | 6.4s | 99.7% | | 185 | qwen2.5-plus ˟ | 649 ±114 | ~$0.05 | 15 | 5-9-1 | 50.1% | 14% | 63.3% | +5.1 | 72.6 | 365 | 6.9s | 98.5% | | 186 | grok-4.1-fast-non-reasoning ˟ | 648 ±125 | ~$0.01 | 15 | 2-7-6 | 50.9% | 14.2% | 36.7% | -4.5 | 41.7 | 142 | 3.0s | 99.5% | | 187 | qwen3-235b-a22b | 646 ±105 | ~$0.23 | 20 | 4-9-7 | 51.3% | 15.3% | 42.5% | -2.5 | 44.6 | 5903 | 149s | 99.5% | | 188 | claude-3-sonnet ˟ | 642 ±158 | ~$0.31 | 6 | 2-3-1 | 53.4% | 14.2% | 58.3% | +9.2 | 81.3 | 258 | 16s | n/a | | 189 | qwen3-coder-plus | 639 ±114 | $0.10 | 16 | 0-12-4 | 50.9% | 16.6% | 37.5% | -4.2 | 70.3 | 151 | 4.5s | 99% | | 190 | claude-sonnet-4 | 639 ±85 | ~$0.27 | 34 | 4-22-8 | 48.5% | 12.8% | 44.1% | -1.4 | 54.5 | 153 | 5.4s | 100% | | 191 | llama-3.1-nemotron-ultra-253b-v1 | 637 ±119 | ~$0.05 | 13 | 2-8-3 | 53.9% | 16.1% | 46.2% | -1.5 | 62.9 | 189 | 11s | 100% | | 192 | ling-2.6-flash | 636 ±123 | ~$0.002 | 19 | 0-7-12 | 54.6% | 12.1% | 18.4% | -11.4 | 47.1 | 150 | 2.0s | 95.5% | | 193 | gemini-2.0-flash-001 ˟ | 636 ±71 | ~$0.008 | 48 | 5-30-13 | 51.2% | 16% | 41.7% | -1.3 | 66.9 | 97 | 1.4s | 100% | | 194 | ernie-4.5-21b-a3b-thinking | 634 ±121 | ~$0.20 | 13 | 5-7-1 | 46.5% | 16.5% | 65.4% | +1.7 | 70.7 | 9531 | 101s | 98% | | 195 | gpt-4-turbo ˟ | 632 ±100 | ~$0.71 | 22 | 3-14-5 | 51.5% | 12.6% | 45.5% | +0.1 | 62.4 | 116 | 4.3s | 99.2% | | 196 | inflection-3-pi | 631 ±124 | ~$0.22 | 12 | 4-8-0 | 48.4% | 16.8% | 66.7% | +6.2 | 72.8 | 107 | 4.2s | 92.9% | | 197 | mistral-large-4.0 | 629 ±136 | $0.17 | 12 | 2-5-5 | 54.7% | 13.8% | 37.5% | -2.8 | 57.6 | 1151 | 26s | 99.6% | | 198 | deepseek-v3 | 629 ±102 | $0.02 | 19 | 3-11-5 | 53.4% | 14.8% | 44.7% | +0.9 | 45.4 | 111 | 5.4s | 99.8% | | 199 | glm-4.6 | 628 ±95 | ~$0.32 | 24 | 4-15-5 | 51.7% | 14.3% | 47.9% | -2.3 | 56.8 | 2461 | 31s | 97.3% | | 200 | intellect-3 | 628 ±134 | ~$0.60 | 10 | 3-6-1 | 49.1% | 14.2% | 60% | +2.4 | 74.2 | 7173 | 76s | 99.6% | | 201 | gemini-1.5-pro ˟ | 627 ±127 | ~$0.07 | 12 | 0-9-3 | 54.1% | 14% | 37.5% | -3 | 50.8 | 67 | 6.9s | 93.4% | | 202 | llama-3.3-nemotron-super-49b-v1.5 | 619 ±128 | ~$0.17 | 11 | 1-9-1 | 49.1% | 13.4% | 50% | -2.7 | 64.1 | 6541 | 80s | 100% | | 203 | minimax-m2.7 | 618 ±123 | $0.24 | 13 | 0-6-7 | 54.4% | 15.5% | 23.1% | -9.4 | 72.5 | 1657 | 39s | 93.4% | | 204 | gpt-4 ˟ | 617 ±120 | $2.07 | 14 | 3-8-3 | 47.9% | 12.7% | 50% | -0.4 | 68.6 | 85 | 3.3s | 98.8% | | 205 | minimax-m2.1 | 615 ±126 | ~$0.26 | 13 | 1-6-6 | 52.5% | 11.5% | 30.8% | -4.5 | 56.8 | 2697 | 50s | 85.6% | | 206 | deepseek-v3-0324 | 613 ±92 | ~$0.02 | 27 | 2-19-6 | 54% | 12.4% | 42.6% | -3 | 56 | 119 | 7.6s | 99.6% | | 207 | qwen3-30b-a3b | 608 ±103 | ~$0.18 | 20 | 2-16-2 | 50.4% | 12.8% | 50% | -1.6 | 72.8 | 6916 | 77s | 100% | | 208 | minimax-m2.5 | 608 ±116 | ~$0.12 | 15 | 3-8-4 | 44.8% | 20.4% | 46.7% | -1.2 | 61.2 | 1085 | 28s | 96% | | 209 | llama-3.3-nemotron-super-49b-v1 | 602 ±133 | ~$0.01 | 10 | 2-8-0 | 49.7% | 13.9% | 60% | +6.8 | 87.9 | 155 | 5.1s | 89.3% | | 210 | grok-3 ˟ | 602 ±99 | ~$0.28 | 21 | 4-12-5 | 48% | 15.6% | 47.6% | -3.1 | 53.4 | 210 | 7.2s | 100% | | 211 | magistral-medium-2506 | 598 ±143 | ~$0.18 | 10 | 2-4-4 | 51% | 13.8% | 40% | -1.5 | 78.9 | 122 | 2.0s | 97.7% | | 212 | gemma-3-12b-it | 596 ±108 | ~$0.004 | 18 | 3-12-3 | 44.1% | 26.1% | 50% | -3.6 | 49.1 | 121 | 6.8s | 99.2% | | 213 | gemini-1.5-flash ˟ | 594 ±131 | ~$0.003 | 10 | 1-8-1 | 44.7% | 17.9% | 50% | +4.7 | 41.8 | 242 | 2.5s | n/a | | 214 | deepseek-v3.1 | 590 ±106 | ~$0.02 | 19 | 3-10-6 | 49.5% | 14.5% | 42.1% | -1.8 | 55.3 | 122 | 11s | 99.6% | | 215 | qwen3-next-80b-a3b-instruct | 590 ±104 | ~$0.02 | 21 | 2-11-8 | 47.9% | 14.7% | 35.7% | -1.9 | 52.9 | 260 | 3.3s | 92% | | 216 | mimo-v2-flash | 589 ±108 | ~$0.07 | 19 | 1-14-4 | 44.2% | 17.1% | 42.1% | -1.3 | 61.4 | 3597 | 9.3s | 96.8% | | 217 | gpt-4o-2024-11-20 | 587 ±98 | ~$0.18 | 26 | 3-14-9 | 49.4% | 13.3% | 38.5% | -6.5 | 61.1 | 89 | 2.1s | 99.8% | | 218 | qwen3-vl-235b-a22b-thinking | 585 ±127 | ~$0.92 | 11 | 2-7-2 | 48% | 15.8% | 50% | +1.2 | 56.6 | 4274 | 82s | 100% | | 219 | mistral-small-4-119b-a6b | 585 ±99 | $0.02 | 21 | 4-13-4 | 46.7% | 15.7% | 50% | 0 | 76.8 | 192 | 2.5s | 86.8% | | 220 | mistral-medium-3.5 | 585 ±122 | $0.17 | 14 | 4-6-4 | 45.1% | 16.8% | 50% | +2 | 55.6 | 242 | 2.4s | 98% | | 221 | devstral-medium | 584 ±121 | ~$0.10 | 13 | 4-8-1 | 44.2% | 17.8% | 61.5% | +0.8 | 75 | 486 | 1.7s | 94.8% | | 222 | glm-4.5-air | 584 ±113 | ~$0.03 | 19 | 7-7-5 | 44% | 18.3% | 55.3% | -0.6 | 61.1 | 350 | 20s | 96.7% | | 223 | gemini-2.0-flash-lite-001 ˟ | 582 ±105 | ~$0.005 | 20 | 1-11-8 | 50% | 14.1% | 32.5% | -1.9 | 59.4 | 69 | 2.5s | 97.9% | | 224 | qwen3-coder-480b-a35b | 581 ±130 | ~$0.05 | 12 | 3-5-4 | 48.9% | 19.8% | 45.8% | -0.3 | 60.6 | 151 | 7.8s | 94.2% | | 225 | qwq-32b | 580 ±128 | ~$0.12 | 13 | 1-7-5 | 46.8% | 14% | 34.6% | -6.3 | 61.8 | 5873 | 154s | 98.2% | | 226 | claude-3-haiku ˟ | 578 ±113 | ~$0.03 | 16 | 4-11-1 | 45.1% | 22.5% | 59.4% | -5.6 | 81.6 | 125 | 6.4s | 99.7% | | 227 | claude-3.5-haiku ˟ | 576 ±97 | ~$0.07 | 23 | 1-15-7 | 59.5% | 16.6% | 37% | -6.4 | 58.1 | 116 | 4.0s | 100% | | 228 | llama-3.1-70b-instruct | 576 ±116 | ~$0.02 | 15 | 1-12-2 | 48.5% | 15.7% | 46.7% | -3.5 | 62.3 | 130 | 6.9s | 98.8% | | 229 | qwen2.5-turbo ˟ | 574 ±116 | ~$0.005 | 14 | 3-9-2 | 48.2% | 18.2% | 53.6% | +5.1 | 84.4 | 89 | 9.1s | 95.8% | | 230 | ling-1t | 574 ±113 | ~$0.07 | 17 | 5-7-5 | 44.2% | 19.5% | 50% | -0.6 | 48.2 | 199 | 6.8s | 90.7% | | 231 | llama-4-maverick | 573 ±94 | ~$0.02 | 27 | 6-12-9 | 45.7% | 17.2% | 44.4% | -0.6 | 58.8 | 243 | 4.7s | 99.4% | | 232 | gpt-3.5-turbo-instruct ˟ | 573 ±114 | $0.07 | 15 | 2-7-6 | 44.7% | 24.4% | 36.7% | -4.9 | 48 | 84 | 1.5s | 87.6% | | 233 | jamba-large-1.7 | 572 ±125 | ~$0.20 | 14 | 3-6-5 | 45.9% | 14.4% | 42.9% | -6.7 | 59 | 212 | 12s | 99.4% | | 234 | lfm2-8b-a1b | 571 ±102 | ~$0.005 | 20 | 7-13-0 | 41.4% | 22.5% | 67.5% | +9.7 | 98.4 | 132 | 1.6s | 91.4% | | 235 | gpt-4.1-nano ˟ | 570 ±102 | ~$0.007 | 20 | 1-13-6 | 48.2% | 15.6% | 37.5% | -3 | 60.2 | 104 | 8.6s | 94.3% | | 236 | inflection-3-productivity | 570 ±128 | ~$0.27 | 11 | 2-8-1 | 46.1% | 20.9% | 54.5% | +5.3 | 87.5 | 113 | 4.4s | 93.3% | | 237 | lfm-2-24b-a2b | 568 ±127 | ~$0.004 | 16 | 0-7-9 | 54.3% | 17.9% | 21.9% | -14.7 | 59.4 | 97 | 1.3s | 54.8% | | 238 | deepseek-v3.1-terminus | 568 ±121 | ~$0.02 | 14 | 4-6-4 | 45.2% | 14.8% | 50% | +0.7 | 52.9 | 123 | 4.7s | 98.5% | | 239 | llama-3.1-405b-instruct | 567 ±92 | ~$0.14 | 25 | 4-13-8 | 44.6% | 15.1% | 42% | -3.1 | 61.9 | 129 | 16s | 97.1% | | 240 | ernie-4.5-21b-a3b | 566 ±106 | ~$0.008 | 18 | 2-14-2 | 48.3% | 18.1% | 50% | +4.3 | 72.5 | 136 | 3.3s | 88.6% | | 241 | hunyuan-a13b-instruct | 563 ±117 | ~$0.02 | 15 | 2-8-5 | 49.1% | 17.6% | 40% | -5.7 | 68.9 | 270 | 3.1s | 71.8% | | 242 | glm-4.7-flash | 562 ±133 | ~$0.81 | 11 | 0-7-4 | 49.1% | 17.8% | 31.8% | -4.4 | 73 | 26355 | 517s | 97.7% | | 243 | qwen3-30b-a3b-thinking-2507 | 561 ±121 | ~$0.21 | 13 | 1-11-1 | 46.4% | 16.7% | 50% | -0.1 | 83.3 | 5995 | 53s | 100% | | 244 | ministral-8b | 560 ±99 | ~$0.009 | 21 | 2-18-1 | 51.8% | 16.7% | 52.4% | +11.4 | 60.6 | 46 | 2.3s | 57.7% | | 245 | mistral-medium-3 | 560 ±124 | ~$0.02 | 19 | 6-4-9 | 51.4% | 19.1% | 42.1% | -3 | 48 | 113 | 4.9s | 99.3% | | 246 | claude-3.5-sonnet ˟ | 556 ±122 | ~$0.24 | 14 | 3-6-5 | 49.1% | 14.6% | 42.9% | -6.4 | 43.9 | 153 | 6.8s | 97.6% | | 247 | nova-2-lite-v1 | 553 ±117 | $0.05 | 14 | 1-10-3 | 47.4% | 15.3% | 42.9% | -2.9 | 81.1 | 142 | 1.7s | 98.2% | | 248 | qwen3-30b-a3b-instruct-2507 | 553 ±96 | ~$0.02 | 23 | 4-14-5 | 47% | 19.7% | 47.8% | -2.8 | 56 | 256 | 6.5s | 95% | | 249 | gemini-1.5-flash-8b ˟ | 552 ±130 | ~<$0.001 | 10 | 1-8-1 | 43.5% | 21.2% | 50% | +6.1 | 43.6 | 95 | 0.9s | 89.5% | | 250 | qwen3-vl-8b-instruct | 552 ±123 | ~$0.02 | 12 | 1-10-1 | 43% | 20.4% | 50% | 0 | 67.9 | 519 | 3.2s | 96.3% | | 251 | lfm-7b ˟ | 550 ±92 | ~<$0.001 | 25 | 1-19-5 | 44.8% | 23.8% | 42% | -6.1 | 80.2 | 85 | 10.0s | 81.6% | | 252 | command-r-plus-08-2024 | 550 ±113 | ~$0.25 | 15 | 2-10-3 | 41.5% | 27.7% | 46.7% | -6.7 | 72.7 | 99 | 17s | 88.2% | | 253 | ernie-4.5-300b-a47b | 549 ±103 | ~$0.03 | 20 | 1-12-7 | 45.9% | 16.7% | 35% | -6 | 69.6 | 140 | 21s | 100% | | 254 | mistral-small-3.2-24b-instruct | 545 ±109 | ~$0.004 | 16 | 1-13-2 | 48.1% | 19.7% | 46.9% | -4 | 79.3 | 110 | 4.6s | 97.8% | | 255 | glm-4-32b | 545 ±107 | ~$0.009 | 17 | 4-10-3 | 45% | 16.3% | 52.9% | +2.7 | 71.4 | 149 | 8.3s | 94.3% | | 256 | claude-3-opus ˟ | 543 ±132 | ~$1.72 | 10 | 1-5-4 | 47.6% | 16.7% | 35% | -5.9 | 64.2 | 130 | 5.7s | 91.7% | | 257 | mistral-medium-3.1 | 541 ±102 | ~$0.13 | 19 | 4-11-4 | 43.2% | 19.9% | 50% | +0.7 | 70.1 | 761 | 14s | 97.3% | | 258 | qwen3-235b-a22b-instruct-2507 | 539 ±96 | ~$0.02 | 27 | 3-13-11 | 47.9% | 12.8% | 35.2% | -2.9 | 52 | 267 | 7.4s | 99.4% | | 259 | gpt-3.5-turbo ˟ | 530 ±116 | $0.04 | 15 | 0-10-5 | 42.5% | 19% | 33.3% | -9.3 | 62.9 | 64 | 1.3s | 89.6% | | 260 | mistral-small-3-24b-instruct-2501 | 530 ±107 | ~$0.004 | 17 | 5-10-2 | 40.3% | 24% | 58.8% | +0.1 | 80.8 | 139 | 2.6s | 97.7% | | 261 | command-r-08-2024 | 529 ±120 | ~$0.02 | 14 | 1-8-5 | 47.1% | 21.4% | 35.7% | -7.8 | 78.9 | 87 | 8.2s | 84.2% | | 262 | qwen3-vl-235b-a22b-instruct | 528 ±125 | ~$0.03 | 12 | 0-7-5 | 45.7% | 18.3% | 29.2% | -2.5 | 58.4 | 129 | 11s | 100% | | 263 | qwen3-vl-32b-instruct | 528 ±156 | ~$0.03 | 11 | 4-1-6 | 44.6% | 21.8% | 40.9% | -8.5 | 47.1 | 301 | 5.6s | 99% | | 264 | gemma-2-9b-it | 518 ±102 | ~$0.006 | 20 | 3-13-4 | 40.4% | 20.5% | 47.5% | +0.3 | 88.7 | 53 | 1.2s | 70.9% | | 265 | wizardlm-2-8x22b | 517 ±126 | ~$0.03 | 13 | 1-6-6 | 48% | 17.8% | 30.8% | -9.4 | 51.2 | 319 | 14s | 96.9% | | 266 | llama-4-scout | 517 ±92 | ~$0.01 | 26 | 1-17-8 | 44.1% | 20.7% | 36.5% | -8.4 | 65.8 | 134 | 5.7s | 100% | | 267 | gemma-3-27b-it | 515 ±103 | ~$0.005 | 23 | 1-12-10 | 51.1% | 18.3% | 30.4% | -3.6 | 47.4 | 142 | 6.5s | 95.3% | | 268 | deepseek-prover-v2 | 511 ±142 | ~$0.03 | 8 | 1-4-3 | 46% | 19.1% | 37.5% | -2.5 | 45.9 | 125 | 8.4s | 98.4% | | 269 | llama-3.1-8b-instruct | 510 ±83 | ~$0.004 | 31 | 8-20-3 | 31.6% | 24.8% | 58.1% | -2.9 | 108.3 | 79 | 1.9s | 85.4% | | 270 | mistral-nemo | 509 ±112 | ~$0.004 | 16 | 2-9-5 | 41.9% | 19.7% | 40.6% | -0.4 | 90 | 54 | 2.4s | 63.1% | | 271 | jamba-large-1.6 | 507 ±156 | ~$0.22 | 6 | 1-3-2 | 42.7% | 24.5% | 41.7% | -6 | 85.3 | 112 | 11s | 98.3% | | 272 | devstral-small | 506 ±121 | ~$0.01 | 13 | 1-7-5 | 47.7% | 19% | 34.6% | -8.5 | 70 | 280 | 2.2s | 97.8% | | 273 | llama-3-8b-instruct | 503 ±116 | ~$0.005 | 14 | 0-12-2 | 44.8% | 23.3% | 42.9% | +0.4 | 111.6 | 76 | 1.9s | 88% | | 274 | magistral-small-2506 | 503 ±130 | ~$0.06 | 11 | 3-5-3 | 42% | 18.8% | 50% | -10.2 | 79.2 | 234 | 2.0s | 98.5% | | 275 | molmo-2-8b | 502 ±122 | ~$0.02 | 12 | 2-7-3 | 44.6% | 20.5% | 45.8% | -3.8 | 93.1 | 97 | 1.4s | 91% | | 276 | olmo-3.1-32b-instruct | 500 ±131 | ~$0.02 | 12 | 1-5-6 | 47.7% | 21.2% | 29.2% | -14.5 | 58.4 | 160 | 9.0s | 98% | | 277 | mistral-small-3.1-24b-instruct | 494 ±101 | ~$0.007 | 20 | 3-12-5 | 38.6% | 25.4% | 45% | +0.9 | 67.2 | 114 | 2.8s | 97.1% | | 278 | qwen3-4b | 493 ±163 | - | 5 | 1-4-0 | 39.7% | 25.5% | 60% | +5.8 | 66.8 | 5161 | 42s | 99.1% | | 279 | kimi-linear-48b-a3b-instruct | 489 ±131 | ~$0.03 | 11 | 1-6-4 | 37.6% | 23.6% | 36.4% | -3.1 | 58.5 | 263 | 4.7s | 84.5% | | 280 | ministral-8b-2512 | 488 ±111 | ~$0.01 | 16 | 2-9-5 | 42.1% | 18.4% | 40.6% | -1.2 | 68 | 448 | 2.9s | 91.9% | | 281 | qwen2.5-7b-instruct | 482 ±110 | ~$0.006 | 16 | 1-13-2 | 43.1% | 22.9% | 46.9% | +8.8 | 82.9 | 80 | 2.7s | 88.5% | | 282 | llama-3.3-8b-instruct ˟ | 470 ±113 | - | 15 | 0-13-2 | 38.5% | 29.6% | 43.3% | -6.5 | 75.6 | 102 | 1.0s | 91.3% | | 283 | llama-3.2-3b-instruct | 467 ±112 | $0.009 | 15 | 0-14-1 | 43.1% | 20.3% | 46.7% | +3.5 | 100.8 | 123 | 1.5s | 60.9% | | 284 | rnj-1-instruct | 465 ±123 | ~$0.01 | 12 | 2-7-3 | 38.7% | 26.6% | 45.8% | +5.2 | 62.8 | 169 | 1.5s | 86.4% | | 285 | granite-4.0-h-micro | 457 ±118 | $0.002 | 13 | 0-13-0 | 39.7% | 24% | 50% | -0.7 | 62.9 | 133 | 4.6s | 77.4% | | 286 | gemma-3-4b-it | 457 ±112 | ~$0.003 | 15 | 0-15-0 | 37.5% | 26.5% | 50% | -2.1 | 78.5 | 93 | 2.1s | 76.2% | | 287 | mistral-small-creative ˟ | 457 ±113 | ~$0.03 | 15 | 3-8-4 | 35.1% | 23% | 46.7% | -0.5 | 72.8 | 1010 | 5.7s | 91.5% | | 288 | olmo-3-7b-think | 453 ±127 | ~$0.40 | 11 | 0-9-2 | 42.6% | 15.8% | 40.9% | -3.1 | 106.3 | 17889 | 114s | 98.8% | | 289 | mythomax-l2-13b | 453 ±120 | ~$0.02 | 13 | 0-9-4 | 41.1% | 23.8% | 34.6% | -13.4 | 87.2 | 142 | 4.0s | 69.5% | | 290 | lfm-2.2-6b | 446 ±119 | ~$0.02 | 14 | 2-8-4 | 34.6% | 21.9% | 42.9% | -0.3 | 110.2 | 379 | 0.9s | 57.2% | | 291 | olmo-2-0325-32b-instruct | 444 ±116 | ~$0.02 | 15 | 1-9-5 | 40.1% | 23.5% | 36.7% | -10.2 | 94.1 | 121 | 6.4s | 93.8% | | 292 | afm-4.5b | 442 ±116 | ~$0.01 | 14 | 2-10-2 | 33.5% | 31.1% | 50% | -8.9 | 97.3 | 85 | 1.1s | 69.1% | | 293 | minimax-m2-her | 440 ±126 | $0.28 | 11 | 3-6-2 | 27.7% | 25.7% | 54.5% | +5.5 | 119.3 | 1339 | 8.8s | 82.3% | | 294 | ministral-3b ˟ | 439 ±106 | ~$0.004 | 17 | 2-14-1 | 32.2% | 34.4% | 52.9% | +6.9 | 65.6 | 46 | 0.6s | 52.3% | | 295 | jamba-mini-1.6 | 430 ±150 | ~$0.02 | 7 | 0-6-1 | 32% | 34.4% | 42.9% | -8.4 | 86 | 97 | 1.2s | 90.8% | | 296 | phi-3-medium-128k-instruct | 425 ±122 | ~$0.07 | 12 | 0-11-1 | 32.8% | 33.3% | 45.8% | -1.1 | 106.9 | 126 | 2.8s | 75% | | 297 | command-r7b-12-2024 | 423 ±102 | $0.009 | 20 | 1-15-4 | 34.8% | 27.2% | 42.5% | -4.2 | 123.3 | 137 | 1.7s | 81.5% | | 298 | olmo-3-7b-instruct | 422 ±120 | ~$0.01 | 17 | 3-6-8 | 36.8% | 23.2% | 35.3% | -6.5 | 72.6 | 143 | 4.1s | 88.6% | | 299 | mistral-7b-instruct-v0.1 | 422 ±123 | ~$0.03 | 12 | 1-9-2 | 28.6% | 42% | 45.8% | -9.8 | 81.7 | 135 | 4.6s | 46.4% | | 300 | random-mover | 419 | - | 200 | 15-170-15 | 28.6% | 30.5% | 50% | 0 | 174.2 | - | - | 100% | | 301 | jamba-mini-1.7 | 416 ±116 | ~$0.03 | 15 | 0-10-5 | 36.6% | 25.1% | 33.3% | -4.3 | 115 | 102 | 3.9s | 90.6% | | 302 | ministral-3b-2512 | 413 ±114 | $0.01 | 15 | 2-7-6 | 37.2% | 25% | 36.7% | -3.5 | 99.7 | 510 | 7.6s | 94.7% | | 303 | lfm-3b ˟ | 412 ±117 | ~$0.002 | 14 | 0-12-2 | 30.5% | 30% | 42.9% | +4.6 | 89 | 76 | 3.9s | 71.2% | | 304 | ui-tars-1.5-7b | 405 ±100 | ~$0.01 | 21 | 1-14-6 | 41.5% | 19.4% | 38.1% | +3.2 | 93 | 96 | 2.1s | 75.8% | | 305 | gemma-3n-e4b-it | 404 ±99 | ~$0.003 | 22 | 0-16-6 | 36.5% | 34.9% | 36.4% | -2.9 | 64 | 90 | 5.2s | 68.9% | ## Detailed Player Statistics: 5+ games, Continuation (220 models) | # | Model | Elo | Cost | Games | W-D-L | Acc | Blunder | WR | Mat | Turns | Tok | Spd | Legal | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 1 | gemini-3-pro-preview ˟ | 1810 ±145 | ~$1.26 | 30 | 26-4-0 | 90.9% | 1.9% | 93.3% | +11.8 | 43.1 | 2348 | 26s | 98.7% | | 2 | gpt-4.5-preview ˟ | 1800 ±255 | ~$1.87 | 20 | 19-0-1 | 89.1% | 2.6% | 95% | +10 | 43 | 161 | 2.6s | 98.7% | | 3 | gemini-3.8-flash | 1767 ±140 | $0.13 | 19 | 14-3-2 | 91.1% | 2.1% | 81.6% | +8.7 | 42.1 | 747 | 8.1s | 99.4% | | 4 | gemini-3.6-flash | 1746 ±160 | $0.26 | 22 | 15-1-6 | 90.3% | 1.8% | 70.5% | +4.9 | 44.6 | 915 | 5.4s | 99.2% | | 5 | gemini-3.7-flash ˟ | 1746 ±155 | $0.07 | 16 | 12-2-2 | 87.3% | 2.3% | 81.3% | +9.6 | 45.8 | 561 | 4.7s | 99.5% | | 6 | gemini-3-flash-preview | 1739 ±113 | $0.03 | 47 | 35-7-5 | 90.9% | 2.3% | 81.9% | +9.7 | 44.6 | 197 | 2.5s | 99.7% | | 7 | gemini-3.1-pro-preview | 1732 ±126 | $0.73 | 31 | 20-2-9 | 88.5% | 2.4% | 67.7% | +5.7 | 43.5 | 1354 | 15s | 99.6% | | 8 | gemini-3.5-flash ˟ | 1706 ±134 | $0.58 | 26 | 19-4-3 | 91% | 1.9% | 80.8% | +6.6 | 40.8 | 1442 | 7.9s | 93.5% | | 9 | gemini-4-argon | 1673 ±138 | $0.21 | 15 | 7-3-5 | 87% | 2.8% | 56.7% | +1.6 | 51.8 | 322 | 5.4s | 98.6% | | 10 | chatgpt-4o-latest ˟ | 1584 ±135 | ~$0.23 | 18 | 9-5-4 | 85.2% | 4.5% | 63.9% | +5.8 | 48 | 204 | 1.3s | 95.3% | | 11 | gpt-6.1-terra | 1577 ±149 | $0.07 | 16 | 9-2-5 | 87.7% | 3.1% | 62.5% | +6.8 | 48.9 | 447 | 4.7s | 99.4% | | 12 | gpt-6-astra | 1534 ±120 | $0.60 | 22 | 10-5-7 | 84.1% | 3.9% | 56.8% | -1.3 | 42.7 | 393 | 7.6s | 98.9% | | 13 | maia5-1500 | 1526 ±121 | - | 23 | 10-4-9 | 84.8% | 2.7% | 52.2% | +3.7 | 40 | - | - | 100% | | 14 | gpt-6.1-sol | 1514 ±134 | $0.15 | 18 | 6-3-9 | 86% | 3% | 41.7% | -1.4 | 56.8 | 442 | 11s | 98.6% | | 15 | gpt-4o | 1492 ±101 | $0.11 | 48 | 31-7-10 | 83.7% | 5% | 71.9% | +5.5 | 39.9 | 184 | 2.1s | 95.8% | | 16 | gpt-5 | 1471 ±124 | $4.08 | 24 | 12-4-8 | 82.9% | 4.6% | 58.3% | +1.4 | 42.9 | 9339 | 154s | 97.8% | | 17 | gpt-5-chat ˟ | 1465 ±117 | ~$0.10 | 36 | 20-5-11 | 83.1% | 4.8% | 62.5% | +5 | 41.3 | 202 | 2.1s | 91.4% | | 18 | gemini-3.5-flash-lite | 1464 ±120 | $0.03 | 25 | 9-5-11 | 79.9% | 4.2% | 46% | +1.2 | 45.4 | 205 | 1.5s | 94.6% | | 19 | gpt-3.5-turbo-instruct ˟ | 1447 ±83 | $0.03 | 110 | 78-7-25 | 78.1% | 6.1% | 74.1% | +4.9 | 32 | 251 | 2.1s | 91.5% | | 20 | claude-opus-5.5 | 1431 ±128 | $0.71 | 20 | 6-4-10 | 81.8% | 3.3% | 40% | -1.8 | 53.6 | 555 | 7.9s | 98.3% | | 21 | gpt-5.5 | 1428 ±141 | $2.53 | 22 | 7-2-13 | 82.2% | 5.4% | 36.4% | -1.3 | 41.1 | 2003 | 35s | 95.6% | | 22 | gpt-5.1-codex ˟ | 1418 ±137 | ~$5.72 | 15 | 5-4-6 | 85.4% | 3.4% | 46.7% | -5.3 | 42.9 | 12364 | 171s | 93.3% | | 23 | gemini-3.1-flash-lite-preview | 1411 ±123 | $0.01 | 37 | 25-2-10 | 82.5% | 3.9% | 70.3% | +6 | 44.4 | 236 | 1.8s | 94% | | 24 | deepseek-v4-pro-0813 | 1388 ±176 | $3.15 | 11 | 5-0-6 | 81.9% | 5.2% | 45.5% | +1.9 | 50.5 | 27579 | 380s | 97.7% | | 25 | gpt-3.5-turbo ˟ | 1382 ±93 | $0.01 | 75 | 52-12-11 | 82.5% | 5.5% | 77.3% | +7.4 | 32.5 | 184 | 2.0s | 92.8% | | 26 | gpt-5.1-chat ˟ | 1363 ±148 | ~$0.15 | 21 | 9-2-10 | 78.4% | 6.2% | 47.6% | +1.4 | 39.4 | 309 | 4.1s | 88.9% | | 27 | deepseek-v4.1-flash | 1356 ±154 | $0.89 | 13 | 5-1-7 | 82.4% | 3.4% | 42.3% | -3.2 | 49.5 | 26240 | 132s | 98.2% | | 28 | gpt-5.1-codex-max ˟ | 1354 ±144 | ~$3.82 | 14 | 4-3-7 | 81.8% | 5.7% | 39.3% | -5.1 | 39.3 | 8773 | 109s | 90.9% | | 29 | o3 | 1353 ±129 | $2.49 | 18 | 5-5-8 | 82.8% | 4.1% | 41.7% | -0.8 | 44 | 6191 | 70s | 89.7% | | 30 | deepseek-v4.1-flash-1017 | 1335 ±143 | $0.63 | 13 | 4-3-6 | 80.6% | 5% | 42.3% | -0.9 | 47.6 | 20168 | 103s | 97.3% | | 31 | gpt-6-sol | 1331 ±130 | $0.36 | 18 | 7-5-6 | 80.4% | 4.4% | 52.8% | +3.4 | 50.5 | 730 | 12s | 95.9% | | 32 | gpt-5.1 | 1321 ±155 | $1.50 | 16 | 9-0-7 | 82.8% | 4.6% | 56.3% | +3.4 | 40 | 3262 | 65s | 88.2% | | 33 | kimi-k3 | 1318 ±164 | ~$8.55 | 15 | 8-1-6 | 79.1% | 5.2% | 56.7% | +2.5 | 41.5 | 13260 | 409s | 97.2% | | 34 | gpt-4o-2024-11-20 | 1315 ±137 | $0.09 | 28 | 16-1-11 | 80.5% | 4.8% | 58.9% | +5.8 | 37 | 173 | 1.6s | 96.7% | | 35 | deepseek-v4-flash-0731 | 1300 ±151 | $0.32 | 19 | 12-1-6 | 76.4% | 5.9% | 65.8% | +7.3 | 39.7 | 26954 | 331s | 89.5% | | 36 | gpt-5-codex ˟ | 1291 ±154 | ~$11.63 | 13 | 8-2-3 | 75.9% | 3.5% | 69.2% | +6.2 | 46.2 | 23242 | 302s | 92.7% | | 37 | claude-fable-5.1 | 1273 ±161 | $2.41 | 11 | 6-2-3 | 76.6% | 6% | 63.6% | +4.9 | 57.6 | 673 | 12s | 93.2% | | 38 | minimax-m3.1-flash | 1262 ±169 | $0.42 | 11 | 7-0-4 | 76.8% | 6.2% | 63.6% | +2.9 | 44.2 | 21079 | 221s | 82.6% | | 39 | gpt-4.1 | 1260 ±105 | ~$0.09 | 40 | 21-7-12 | 80.5% | 3.3% | 61.3% | +8.6 | 39.5 | 198 | 2.5s | 97.2% | | 40 | glm-5.3-flash | 1260 ±181 | $0.58 | 7 | 3-1-3 | 79.6% | 6% | 50% | -2.3 | 45.9 | 31548 | 512s | 85.8% | | 41 | gpt-5.4 | 1259 ±138 | ~$0.17 | 21 | 10-3-8 | 79.1% | 5.3% | 54.8% | +4.2 | 40 | 211 | 2.8s | 91.9% | | 42 | gpt-4 ˟ | 1252 ±155 | $0.97 | 18 | 9-1-8 | 81.9% | 4.3% | 52.8% | 0 | 45.4 | 195 | 6.2s | 94.8% | | 43 | gpt-4.1-mini | 1246 ±119 | $0.05 | 32 | 18-5-9 | 73.4% | 7.4% | 64.1% | -0.3 | 40.2 | 368 | 3.6s | 61.5% | | 44 | claude-sonnet-5.5 | 1211 ±164 | $0.53 | 14 | 4-0-10 | 81% | 4.3% | 28.6% | -5.1 | 54 | 759 | 7.4s | 89.7% | | 45 | qwen3.8-max | 1211 ±178 | ~$5.98 | 12 | 8-0-4 | 76.4% | 5.8% | 66.7% | +5.5 | 45.8 | 21337 | 437s | 98.7% | | 46 | gpt-5.6-sol | 1206 ±112 | $1.27 | 24 | 6-8-10 | 76.1% | 6.4% | 41.7% | -1.8 | 44 | 931 | 18s | 90.4% | | 47 | gemini-2.0-flash-001 ˟ | 1184 ±130 | ~$0.007 | 24 | 10-4-10 | 74.5% | 7.3% | 50% | +1.5 | 43.1 | 297 | 1.8s | 88.2% | | 48 | claude-fable-5 | 1157 ±147 | ~$2.15 | 20 | 12-1-7 | 68% | 8.5% | 62.5% | +5.2 | 44.9 | 818 | 14s | 94.5% | | 49 | gpt-5.2-codex ˟ | 1151 ±145 | ~$1.61 | 14 | 3-4-7 | 74.6% | 6.2% | 35.7% | -5.9 | 43.1 | 2390 | 37s | 86.1% | | 50 | gpt-5-mini | 1099 ±113 | ~$0.46 | 21 | 3-9-9 | 72.8% | 9.4% | 35.7% | -3 | 49.7 | 4189 | 62s | 91.7% | | 51 | grok-4.20-reasoning | 1087 ±144 | ~$1.04 | 14 | 3-7-4 | 70.4% | 7.5% | 46.4% | +0.6 | 49 | 2723 | 17s | 81% | | 52 | claude-opus-4.1 | 1078 ±128 | ~$2.08 | 23 | 8-5-10 | 72.3% | 7.8% | 45.7% | +2.2 | 50.2 | 364 | 8.9s | 82.1% | | 53 | gpt-5.3-codex | 1073 ±149 | ~$0.98 | 11 | 1-4-6 | 73.7% | 7.5% | 27.3% | -6.5 | 41.8 | 1413 | 25s | 86.7% | | 54 | gpt-5.6-terra | 1072 ±130 | $0.53 | 18 | 2-6-10 | 69.2% | 6.2% | 27.8% | -1.6 | 46.1 | 703 | 9.3s | 82.2% | | 55 | gpt-5.6-luna | 1067 ±136 | $0.28 | 17 | 3-5-9 | 71.7% | 9.8% | 32.4% | -6 | 41.5 | 1181 | 11s | 83% | | 56 | gemini-2.5-pro | 1059 ±139 | ~$1.18 | 28 | 4-3-21 | 72.4% | 7.5% | 19.6% | -3.9 | 40.7 | 2686 | 60s | 86.7% | | 57 | gpt-5-nano | 1052 ±132 | ~$0.20 | 19 | 6-9-4 | 68.8% | 8% | 55.3% | +6.5 | 42.2 | 11288 | 79s | 94.2% | | 58 | hy3 | 1032 ±131 | $0.21 | 15 | 7-6-2 | 71.6% | 9.2% | 66.7% | +8.2 | 47 | 7014 | 113s | 93.2% | | 59 | gpt-4-turbo ˟ | 1018 ±137 | ~$0.59 | 20 | 6-4-10 | 69.8% | 7.4% | 40% | +0.7 | 40.9 | 270 | 5.9s | 81.1% | | 60 | o4-mini ˟ | 1007 ±168 | ~$1.24 | 13 | 5-2-6 | 68.1% | 7.2% | 46.2% | -0.4 | 43.2 | 5065 | 69s | 78.9% | | 61 | qwen3.8-flash | 1005 ±174 | $0.89 | 10 | 7-1-2 | 65.7% | 9.2% | 75% | +6 | 46.1 | 38722 | 398s | 94.1% | | 62 | grok-4 ˟ | 992 ±158 | ~$7.09 | 12 | 0-5-7 | 68% | 6.9% | 20.8% | -1.3 | 40.4 | 10883 | 325s | 94.3% | | 63 | o1 ˟ | 989 ±210 | ~$5.80 | 7 | 1-0-6 | 70.6% | 8.1% | 14.3% | -11.1 | 44.6 | 1644 | 19s | 79.1% | | 64 | grok-4.7 | 977 ±159 | $1.51 | 11 | 7-2-2 | 65.5% | 10.7% | 72.7% | +9.5 | 53.1 | 5021 | 78s | 92.5% | | 65 | muse-spark-1.3 | 965 ±151 | $1.28 | 10 | 5-3-2 | 69.4% | 8.1% | 65% | +7.8 | 48.2 | 5708 | 50s | 93.2% | | 66 | laguna-s-2.1 | 962 ±173 | $0.19 | 9 | 1-1-7 | 73.6% | 11.1% | 16.7% | -15.1 | 29.7 | 23322 | 238s | 53.1% | | 67 | claude-opus-5 | 955 ±137 | $1.37 | 17 | 6-4-7 | 69.5% | 8.8% | 47.1% | -0.8 | 52.5 | 873 | 12s | 93.4% | | 68 | gpt-5.2 | 955 ±169 | ~$2.24 | 13 | 3-2-8 | 67.8% | 8.9% | 30.8% | -7.2 | 41.2 | 3083 | 66s | 80.6% | | 69 | gpt-5.3-chat ˟ | 948 ±137 | ~$0.55 | 17 | 1-6-10 | 67.7% | 9.5% | 23.5% | -8.5 | 41.5 | 704 | 8.0s | 78.4% | | 70 | gpt-4o-mini | 931 ±135 | $0.05 | 18 | 6-5-7 | 69.5% | 9.6% | 47.2% | -2.5 | 47.7 | 683 | 5.7s | 51.4% | | 71 | claude-opus-4.7 | 925 ±126 | ~$1.01 | 21 | 6-6-9 | 65% | 11.2% | 42.9% | -0.8 | 52.5 | 445 | 4.5s | 72.5% | | 72 | gemini-2.5-flash | 913 ±129 | ~$0.07 | 26 | 9-6-11 | 70.5% | 8.2% | 46.2% | +2.2 | 46.9 | 483 | 3.5s | 90.2% | | 73 | claude-opus-4.5 | 908 ±117 | ~$0.91 | 21 | 5-8-8 | 63.2% | 12.6% | 42.9% | -1.9 | 59.7 | 382 | 4.8s | 78.8% | | 74 | grok-4.1-fast-reasoning ˟ | 906 ±133 | ~$0.20 | 14 | 7-5-2 | 66.4% | 10.4% | 67.9% | +7.4 | 56.3 | 5874 | 78s | 78.6% | | 75 | gpt-oss-20b | 903 ±128 | ~$0.06 | 20 | 5-7-8 | 69.6% | 12.5% | 42.5% | -3.3 | 41.9 | 7552 | 32s | 86% | | 76 | claude-sonnet-5 | 896 ±124 | $2.16 | 16 | 6-6-4 | 64.5% | 9.1% | 56.3% | +0.5 | 50.9 | 3524 | 41s | 85.4% | | 77 | claude-opus-4 ˟ | 889 ±126 | ~$2.12 | 22 | 6-7-9 | 60.1% | 12.4% | 43.2% | +3.4 | 53.6 | 380 | 8.6s | 87.9% | | 78 | gpt-6-luna | 888 ±137 | $0.06 | 13 | 1-6-6 | 69% | 9.2% | 30.8% | -8.5 | 57.1 | 1692 | 17s | 83.3% | | 79 | gemini-1.5-pro ˟ | 888 ±166 | ~$0.21 | 10 | 3-4-3 | 64% | 9.9% | 50% | +2.9 | 66.3 | 288 | 3.7s | 75.6% | | 80 | qwen3.7-max | 875 ±134 | ~$0.68 | 17 | 9-5-3 | 59.7% | 10.7% | 67.6% | +11.6 | 50.6 | 2140 | 33s | 91.1% | | 81 | o1-mini ˟ | 869 ±185 | ~$0.21 | 8 | 0-1-7 | 68.5% | 9.8% | 6.3% | -19 | 55.4 | 821 | 15s | 72% | | 82 | muse-spark-1.3-contributor | 846 ±153 | $0.08 | 11 | 7-2-2 | 58.5% | 8.7% | 72.7% | +3 | 55.8 | 6331 | 59s | 91.9% | | 83 | gpt-5.2-chat ˟ | 842 ±135 | ~$0.75 | 16 | 2-7-7 | 62.4% | 10.1% | 34.4% | -5.1 | 54.5 | 739 | 11s | 80.4% | | 84 | codex-mini ˟ | 835 ±163 | ~$2.51 | 10 | 3-3-4 | 62.6% | 12.4% | 45% | +0.9 | 44 | 6224 | 43s | 66.3% | | 85 | seed-2.0-mini | 835 ±137 | $0.28 | 11 | 1-6-4 | 62.1% | 13.3% | 36.4% | -10.8 | 50.8 | 6905 | 131s | 52.2% | | 86 | minimax-m2 | 826 ±145 | ~$1.10 | 13 | 0-6-7 | 62.5% | 14.8% | 23.1% | -10.1 | 50.5 | 11665 | 157s | 56.8% | | 87 | seed-2.0-lite | 820 ±147 | ~$0.22 | 10 | 3-4-3 | 63.6% | 11.2% | 50% | -3.9 | 46.6 | 1300 | 28s | 57.6% | | 88 | deepseek-v3.2-speciale | 819 ±181 | ~$0.42 | 10 | 3-1-6 | 61.9% | 11.7% | 35% | -7.6 | 36.2 | 18463 | 380s | 79.2% | | 89 | gpt-5.1-codex-mini ˟ | 811 ±166 | ~$0.79 | 11 | 3-2-6 | 62.9% | 8.9% | 36.4% | -2.4 | 37.1 | 5348 | 46s | 78.6% | | 90 | claude-haiku-5.5 | 805 ±140 | $0.05 | 13 | 1-4-8 | 66.7% | 10.3% | 23.1% | -9.3 | 44.5 | 1753 | 8.8s | 80.3% | | 91 | lfm-7b ˟ | 795 ±154 | - | 11 | 0-8-3 | 53.2% | 24.8% | 36.4% | -14.5 | 96.4 | - | 5.1s | n/a | | 92 | claude-opus-4.6 | 794 ±126 | ~$0.60 | 22 | 5-6-11 | 56.1% | 12.1% | 36.4% | -5.2 | 51.4 | 297 | 4.9s | 80.4% | | 93 | muse-spark-1.2 | 784 ±110 | ~$0.90 | 16 | 3-10-3 | 58.5% | 10.7% | 50% | +4 | 49.6 | 3742 | 20s | 88.8% | | 94 | claude-opus-4.8 | 782 ±124 | ~$0.74 | 18 | 1-7-10 | 61.4% | 8.7% | 25% | -5.7 | 55.4 | 352 | 4.3s | 84.1% | | 95 | muse-spark-1.2-contributor | 779 ±110 | $0.04 | 16 | 4-10-2 | 59% | 11.6% | 56.3% | -1.3 | 50.8 | 3679 | 27s | 90.8% | | 96 | kimi-k2.6 | 774 ±139 | ~$3.57 | 14 | 8-4-2 | 55% | 12.3% | 71.4% | +5.4 | 51.9 | 16044 | 295s | 90% | | 97 | grok-4-fast-reasoning ˟ | 768 ±130 | ~$0.08 | 15 | 1-8-6 | 63.2% | 8.1% | 33.3% | -0.5 | 56.3 | 2253 | 31s | 71.5% | | 98 | grok-3 ˟ | 766 ±123 | ~$0.30 | 18 | 1-14-3 | 61% | 10.1% | 44.4% | +5.6 | 60.2 | 215 | 4.9s | 84.1% | | 99 | qwen3-14b | 762 ±177 | ~$0.08 | 5 | 0-4-1 | 61.5% | 14.5% | 40% | -14.4 | 47.2 | 3132 | 101s | 50.6% | | 100 | muse-spark-1.1 | 756 ±114 | $1.35 | 17 | 6-8-3 | 52.2% | 12.5% | 58.8% | +5.5 | 52.8 | 4915 | 25s | 83.4% | | 101 | grok-2-latest ˟ | 744 ±151 | ~$0.15 | 8 | 1-6-1 | 58.1% | 13.1% | 50% | -2.1 | 42 | 188 | - | 67.1% | | 102 | kimi-k2.5 | 739 ±133 | ~$0.86 | 16 | 4-5-7 | 57.9% | 17.3% | 40.6% | +1.6 | 50.4 | 4834 | 109s | 77.1% | | 103 | claude-sonnet-4 | 737 ±117 | ~$0.51 | 20 | 1-9-10 | 54.1% | 15.4% | 27.5% | -4 | 52 | 373 | 4.0s | 71.1% | | 104 | kimi-k2.7-code | 734 ±145 | ~$3.28 | 10 | 2-4-4 | 60.2% | 14.1% | 40% | -1.7 | 51.6 | 13834 | 258s | 85.4% | | 105 | gemini-2.5-flash-lite | 729 ±134 | ~$0.05 | 18 | 5-6-7 | 64% | 15.4% | 44.4% | -0.5 | 52.2 | 1972 | 2.0s | 86.7% | | 106 | minimax-m2.1 | 728 ±140 | ~$1.48 | 10 | 0-7-3 | 60.3% | 13.9% | 35% | -12.5 | 59.9 | 8562 | 80s | 47.8% | | 107 | o3-mini ˟ | 708 ±145 | ~$1.49 | 11 | 0-4-7 | 61.4% | 10% | 18.2% | -12.5 | 58.6 | 3078 | 41s | 56.6% | | 108 | claude-3.7-sonnet ˟ | 707 ±126 | ~$0.98 | 14 | 0-12-2 | 54.7% | 15.9% | 42.9% | -1.9 | 72.9 | 539 | 5.7s | 77.3% | | 109 | kimi-k2 | 707 ±118 | $0.07 | 20 | 3-9-8 | 52.9% | 19.4% | 37.5% | -6.1 | 52 | 433 | 11s | 69.5% | | 110 | hy3-preview | 696 ±164 | ~$0.37 | 10 | 1-4-5 | 56.9% | 9.9% | 30% | -8.4 | 52.4 | 9622 | 99s | 83.7% | | 111 | claude-sonnet-4.6 | 696 ±118 | $0.70 | 19 | 4-8-7 | 50% | 16.6% | 42.1% | -2.2 | 65.8 | 388 | 4.6s | 68.7% | | 112 | grok-4.6 | 693 ±173 | $1.08 | 8 | 1-3-4 | 56.2% | 10.6% | 31.3% | -4.4 | 55.8 | 2476 | 44s | 83.5% | | 113 | kimi-k2-thinking | 687 ±129 | ~$3.83 | 14 | 6-5-3 | 47.7% | 15.7% | 60.7% | +1.6 | 59.9 | 12371 | 315s | 69% | | 114 | grok-build-0.1 | 686 ±140 | ~$0.89 | 11 | 1-7-3 | 59.2% | 10.9% | 40.9% | +5.8 | 53.6 | 6523 | 43s | 80.9% | | 115 | glm-5 | 671 ±140 | ~$2.15 | 13 | 1-6-6 | 56.6% | 14.2% | 30.8% | -3.5 | 62.8 | 8330 | 185s | 75.3% | | 116 | muse-glimmer-30b | 667 ±131 | $0.73 | 12 | 1-10-1 | 54.3% | 11.7% | 50% | +6.4 | 50.8 | 7725 | 112s | 78.1% | | 117 | ling-2.6-1t | 665 ±152 | ~$0.43 | 10 | 0-6-4 | 54.5% | 19.6% | 30% | -11.3 | 55.8 | 11928 | 84s | 57.4% | | 118 | gemini-2.0-flash-lite-001 ˟ | 663 ±133 | ~$0.004 | 14 | 4-6-4 | 57.1% | 14.8% | 50% | +2.3 | 60.3 | 103 | 1.7s | 62.4% | | 119 | minimax-m2.7 | 661 ±176 | ~$2.00 | 5 | 1-3-1 | 53.4% | 14.4% | 50% | +3.4 | 52.8 | 18013 | 429s | 63.3% | | 120 | nemotron-3.5-super-vl | 657 ±160 | - | 8 | 0-4-4 | 54.1% | 21% | 25% | -11.6 | 56.3 | 8262 | 107s | 75.6% | | 121 | claude-3.5-sonnet ˟ | 655 ±142 | ~$0.51 | 11 | 2-5-4 | 51.7% | 17.3% | 40.9% | 0 | 61 | 338 | 4.8s | 82.6% | | 122 | grok-4.5 | 652 ±141 | $0.73 | 13 | 1-9-3 | 48.3% | 13.3% | 42.3% | -3.8 | 56.9 | 1742 | 18s | 86.6% | | 123 | qwen3-plus-07-28 | 648 ±152 | ~$0.04 | 11 | 0-4-7 | 57.7% | 14.1% | 18.2% | -11.2 | 47.8 | 319 | 2.6s | 67.3% | | 124 | deepseek-v4-flash | 644 ±135 | ~$0.15 | 12 | 0-8-4 | 54.4% | 14.4% | 33.3% | -9.9 | 65.9 | 6192 | 82s | 71.2% | | 125 | claude-sonnet-4.5 | 638 ±115 | ~$0.34 | 19 | 4-9-6 | 58.1% | 10.1% | 44.7% | +1.9 | 46.6 | 287 | 3.7s | 76% | | 126 | hunyuan-a13b-instruct | 637 ±136 | ~$0.06 | 10 | 0-6-4 | 60.2% | 17.3% | 30% | -25.5 | 51.2 | 648 | 6.7s | 37.8% | | 127 | claude-haiku-4.5 | 637 ±132 | $0.22 | 18 | 1-6-11 | 57.2% | 19.2% | 22.2% | -12.7 | 48.9 | 365 | 2.1s | 51.6% | | 128 | glm-5.1 | 636 ±162 | ~$3.27 | 9 | 4-2-3 | 47.2% | 22.6% | 55.6% | +1.1 | 58.7 | 11122 | 208s | 81.6% | | 129 | deepseek-v3 | 633 ±124 | ~$0.07 | 12 | 0-12-0 | 48.4% | 20.5% | 50% | -0.8 | 75.6 | 381 | 11s | 67.2% | | 130 | glm-5.2 | 631 ±129 | ~$2.44 | 13 | 4-5-4 | 48.8% | 18.3% | 50% | +4.1 | 55.2 | 8541 | 117s | 78.7% | | 131 | qwen3-235b-a22b | 630 ±157 | ~$0.75 | 10 | 2-3-5 | 55.6% | 19.3% | 35% | -9 | 52.7 | 8262 | 131s | 49.7% | | 132 | gpt-oss-120b | 629 ±140 | ~$0.17 | 14 | 0-10-4 | 49.1% | 14.4% | 35.7% | -1.6 | 60.4 | 4049 | 30s | 87.4% | | 133 | deepseek-v3-0324 | 627 ±126 | ~$0.03 | 14 | 3-7-4 | 52.7% | 17.7% | 46.4% | +1.9 | 57.9 | 248 | 12s | 67.8% | | 134 | mistral-large-4.0 | 624 ±151 | $0.06 | 9 | 0-4-5 | 55.2% | 16.6% | 22.2% | -6.9 | 45.9 | 211 | 5.0s | 60.4% | | 135 | grok-code-fast-1 ˟ | 621 ±141 | ~$0.74 | 10 | 1-8-1 | 49.7% | 14.1% | 50% | +6.9 | 68.4 | 3798 | 32s | 54% | | 136 | deepseek-v4-pro | 619 ±148 | ~$1.55 | 12 | 4-4-4 | 51.4% | 16.3% | 50% | -4.4 | 52.4 | 10995 | 246s | 79.4% | | 137 | grok-4.3 | 612 ±127 | $0.58 | 13 | 2-8-3 | 52.3% | 14.7% | 46.2% | +1.1 | 56.9 | 3026 | 34s | 78.7% | | 138 | llama-3.3-70b-instruct | 612 ±130 | ~$0.03 | 14 | 0-9-5 | 47.1% | 35.3% | 32.1% | -11.5 | 68.2 | 439 | 7.9s | 49.5% | | 139 | gemma-4-26b-a4b-it | 607 ±119 | ~$0.03 | 13 | 1-10-2 | 53.9% | 19.8% | 46.2% | -2.1 | 54.6 | 559 | 8.8s | 51.8% | | 140 | gemma-2-27b-it | 604 ±138 | ~$0.05 | 10 | 0-9-1 | 49.3% | 25.1% | 45% | -5.9 | 49.1 | 289 | 6.8s | 44.3% | | 141 | devstral-2512 | 604 ±142 | ~$0.22 | 9 | 2-6-1 | 46.8% | 17.7% | 55.6% | +1 | 67.9 | 897 | 2.0s | 61.2% | | 142 | nemotron-3.5-lightning | 600 ±166 | - | 6 | 0-3-3 | 51.8% | 21.3% | 25% | -21.5 | 54.3 | 4759 | 51s | 39.3% | | 143 | deepseek-v3.2 | 595 ±124 | ~$0.01 | 13 | 3-8-2 | 43.3% | 25.9% | 53.8% | -1 | 49 | 292 | 18s | 62.1% | | 144 | nemotron-3-nano-30b-a3b | 594 ±135 | ~$0.40 | 9 | 1-8-0 | 48.3% | 17.2% | 55.6% | +6.7 | 79.7 | 12120 | 48s | 49.1% | | 145 | mimo-v2-pro ˟ | 592 ±142 | ~$2.99 | 8 | 0-8-0 | 51.3% | 15.8% | 50% | +1.9 | 74.9 | 8714 | 114s | 66.4% | | 146 | qwen3.5-397b-a17b | 587 ±135 | ~$1.32 | 11 | 2-5-4 | 49.9% | 25% | 40.9% | -5.8 | 58.5 | 5604 | 87s | 83.7% | | 147 | north-mini-code | 587 ±150 | - | 7 | 0-7-0 | 47.3% | 25.3% | 50% | -4.9 | 91.6 | 18925 | 167s | 45.9% | | 148 | gpt-4.1-nano ˟ | 582 ±144 | ~$0.07 | 9 | 1-7-1 | 45.4% | 19.5% | 50% | -5 | 98.6 | 399 | 2.8s | 27.2% | | 149 | qwen3-next-80b-a3b-thinking | 569 ±142 | ~$0.71 | 10 | 1-5-4 | 50.1% | 22.6% | 35% | -7.5 | 38.5 | 7573 | 45s | 50.6% | | 150 | gemma-4-31b-it | 568 ±123 | ~$0.01 | 12 | 2-8-2 | 46.9% | 23.1% | 50% | +8.3 | 41 | 202 | 25s | 63.6% | | 151 | step-3.7-flash | 568 ±156 | ~$3.17 | 6 | 2-4-0 | 45.8% | 18.6% | 66.7% | +3.3 | 58.7 | 30087 | 222s | 64.5% | | 152 | longcat-2.0 | 566 ±137 | ~$6.15 | 9 | 0-8-1 | 45.9% | 13.5% | 44.4% | -3.9 | 94.3 | 32587 | 370s | 60.6% | | 153 | deepseek-v3.2-exp | 565 ±153 | ~$0.01 | 7 | 0-5-2 | 51.9% | 16% | 35.7% | +4.4 | 50.4 | 211 | 11s | 56.2% | | 154 | mimo-v2-omni | 554 ±153 | ~$1.70 | 8 | 3-3-2 | 41.1% | 19.1% | 56.3% | +3.3 | 75.9 | 6904 | 53s | 62.3% | | 155 | kimi-k2-0905 | 548 ±121 | ~$0.10 | 17 | 0-12-5 | 40.5% | 22.4% | 35.3% | -0.5 | 64.2 | 339 | 9.5s | 69.5% | | 156 | qwen3-next-80b-a3b-instruct | 547 ±136 | ~$0.06 | 11 | 0-8-3 | 44% | 21.8% | 36.4% | -6.1 | 54.8 | 511 | 2.9s | 52.6% | | 157 | step-3.5-flash | 547 ±135 | ~$0.52 | 12 | 2-5-5 | 43.5% | 17.9% | 37.5% | +3.3 | 48.3 | 25719 | 182s | 72.1% | | 158 | qwen3.5-plus-02-15 | 546 ±136 | ~$0.16 | 10 | 3-7-0 | 36% | 19.4% | 65% | +4.7 | 68.1 | 729 | 13s | 68.9% | | 159 | grok-3-mini ˟ | 545 ±135 | ~$0.15 | 10 | 3-7-0 | 36.6% | 23.7% | 65% | +4.2 | 51.2 | 1362 | 13s | 60.5% | | 160 | grok-4-fast-non-reasoning ˟ | 540 ±128 | ~$0.04 | 13 | 1-10-2 | 40.5% | 16.5% | 46.2% | -1.7 | 75.7 | 300 | 2.0s | 54.6% | | 161 | llama-4-scout | 536 ±128 | ~$0.05 | 11 | 1-10-0 | 40.1% | 24.3% | 54.5% | -6.8 | 90.1 | 459 | 4.5s | 41.8% | | 162 | longcat-flash-chat | 535 ±142 | ~$0.04 | 10 | 0-6-4 | 50.2% | 21.2% | 30% | -6.2 | 48.1 | 636 | 4.8s | 65.9% | | 163 | qwen3-max | 534 ±147 | ~$0.41 | 11 | 0-8-3 | 43.6% | 25% | 36.4% | -4.7 | 71.8 | 487 | 7.3s | 62.3% | | 164 | qwen3.6-flash | 532 ±182 | ~$0.52 | 6 | 0-4-2 | 42.5% | 19.2% | 33.3% | -7.7 | 61.7 | 4267 | 28s | 58.5% | | 165 | qwen3.5-35b-a3b | 529 ±127 | ~$1.10 | 11 | 1-10-0 | 40.8% | 18.3% | 54.5% | +2.8 | 83.5 | 7382 | 66s | 69.3% | | 166 | mistral-large-2-2411 | 523 ±150 | ~$0.79 | 11 | 0-7-4 | 42% | 25% | 31.8% | -8.6 | 95.1 | 515 | 7.7s | 52.3% | | 167 | llama-4-maverick | 522 ±124 | ~$0.06 | 14 | 1-9-4 | 44.2% | 18.2% | 39.3% | -6.6 | 83.4 | 386 | 3.5s | 49.6% | | 168 | llama-3.1-405b-instruct | 520 ±138 | ~$0.52 | 10 | 0-8-2 | 44% | 19.3% | 40% | -0.6 | 102.5 | 539 | 11s | 62.9% | | 169 | qwen3.5-122b-a10b | 515 ±154 | ~$2.06 | 7 | 2-4-1 | 41.2% | 17.5% | 57.1% | +5.1 | 75.6 | 7888 | 67s | 68.7% | | 170 | glm-4-32b | 514 ±144 | ~$0.04 | 9 | 0-7-2 | 44.3% | 26.4% | 38.9% | -3.4 | 79.2 | 756 | 4.8s | 44% | | 171 | gemma-3-27b-it | 505 ±157 | ~$0.02 | 9 | 0-3-6 | 46.8% | 23.7% | 16.7% | -19.1 | 58.7 | 461 | 8.3s | 49.1% | | 172 | qwen3-coder-480b-a35b | 505 ±135 | ~$0.35 | 10 | 1-8-1 | 40.5% | 22.2% | 50% | -2.2 | 78.2 | 1817 | 13s | 58.4% | | 173 | ling-2.6-flash | 504 ±179 | ~$0.05 | 6 | 0-2-4 | 46% | 20.9% | 16.7% | -15.3 | 33 | 4764 | 29s | 49.4% | | 174 | mistral-large-3-2512 | 504 ±119 | ~$0.19 | 13 | 4-8-1 | 35.6% | 25.5% | 61.5% | +6.2 | 103 | 514 | 7.7s | 58.1% | | 175 | minimax-m3 | 504 ±166 | $1.26 | 8 | 4-2-2 | 33.2% | 22.4% | 62.5% | +6.6 | 57.5 | 12813 | 245s | 71.7% | | 176 | mimo-v2-flash | 503 ±123 | ~$0.02 | 12 | 0-11-1 | 41.2% | 26.7% | 45.8% | -1.8 | 71 | 631 | 2.8s | 66.7% | | 177 | command-r-08-2024 | 503 ±161 | ~$0.09 | 7 | 1-3-3 | 41.2% | 24.8% | 35.7% | -12.6 | 88.9 | 582 | 4.4s | 42.2% | | 178 | nemotron-3-ultra-550b-a55b | 498 ±154 | ~$1.17 | 6 | 0-4-2 | 46.2% | 22.9% | 33.3% | -5.2 | 78.3 | 2975 | 178s | 60.9% | | 179 | grok-4.1-fast-non-reasoning ˟ | 495 ±128 | ~$0.04 | 12 | 1-8-3 | 37.8% | 23.7% | 41.7% | -7 | 71.8 | 341 | 2.4s | 48.1% | | 180 | qwen3.7-flash | 493 ±167 | ~$0.10 | 7 | 0-4-3 | 41.1% | 22.5% | 28.6% | -9.6 | 86 | 5105 | 36s | 59% | | 181 | ernie-4.5-300b-a47b | 493 ±150 | ~$0.11 | 9 | 0-7-2 | 36.6% | 31.2% | 38.9% | -2.2 | 119.4 | 339 | 9.6s | 52.8% | | 182 | qwen3.6-plus | 491 ±130 | ~$0.95 | 11 | 0-10-1 | 38.4% | 23.7% | 45.5% | +1.7 | 82.5 | 4382 | 84s | 76% | | 183 | jamba-large-1.7 | 489 ±135 | ~$0.78 | 10 | 0-8-2 | 41.8% | 27.5% | 40% | -9.6 | 84.5 | 380 | 5.5s | 43.3% | | 184 | deepseek-r1 | 487 ±166 | ~$2.09 | 5 | 0-5-0 | 37% | 22.6% | 50% | -9.4 | 76.2 | 6489 | 214s | 61.9% | | 185 | jamba-large-1.6 | 481 ±172 | - | 5 | 0-4-1 | 39.8% | 34.7% | 40% | -6.4 | 90.8 | - | 4.6s | n/a | | 186 | qwen3.5-27b | 480 ±141 | ~$1.37 | 8 | 1-6-1 | 37.6% | 31.3% | 50% | +4.9 | 57.6 | 7200 | 86s | 68.4% | | 187 | qwen2.5-72b-instruct | 476 ±134 | ~$0.05 | 11 | 0-10-1 | 36.2% | 24% | 45.5% | -5.9 | 90.1 | 507 | 8.0s | 53% | | 188 | mimo-v2.5-pro | 475 ±164 | ~$2.94 | 5 | 0-4-1 | 39.9% | 21.5% | 40% | -3.8 | 91.6 | 7694 | 104s | 71.4% | | 189 | qwen3.6-35b-a3b | 473 ±162 | ~$0.61 | 7 | 0-3-4 | 42.8% | 20% | 21.4% | -16.6 | 58.9 | 4859 | 55s | 63.5% | | 190 | grok-4.20-non-reasoning | 470 ±142 | ~$0.23 | 10 | 0-6-4 | 40.1% | 20.6% | 30% | -0.4 | 62.5 | 294 | 1.6s | 63.1% | | 191 | qwen3.6-27b | 467 ±154 | ~$2.22 | 7 | 1-3-3 | 41.3% | 17.6% | 35.7% | -2.9 | 56.9 | 10716 | 218s | 72% | | 192 | deepseek-v3.1 | 465 ±146 | ~$0.07 | 9 | 2-4-3 | 35.4% | 29.1% | 44.4% | 0 | 86.3 | 445 | 12s | 71% | | 193 | phi-4 | 463 ±155 | ~$0.02 | 7 | 0-7-0 | 36.1% | 37.6% | 50% | -3.7 | 71.7 | 552 | 8.2s | 48.7% | | 194 | mimo-v2.5 | 463 ±168 | ~$1.58 | 6 | 2-2-2 | 35.1% | 23.2% | 50% | -1.5 | 74 | 7182 | 50s | 64.7% | | 195 | qwen3-30b-a3b-instruct-2507 | 449 ±153 | ~$0.19 | 7 | 0-6-1 | 37.6% | 27.1% | 42.9% | -4.6 | 77.7 | 1186 | 11s | 35.9% | | 196 | glm-4.5 | 447 ±131 | ~$0.21 | 10 | 0-10-0 | 32.9% | 34.2% | 50% | -4.7 | 71.9 | 681 | 20s | 52% | | 197 | glm-4.5-air | 445 ±143 | ~$0.02 | 8 | 0-8-0 | 34.4% | 29% | 50% | -13.1 | 68.4 | 93 | 12s | 41.4% | | 198 | qwen2.5-plus ˟ | 439 ±137 | ~$0.06 | 9 | 1-7-1 | 33% | 23.6% | 50% | +5.1 | 71.9 | 335 | 6.6s | 60.9% | | 199 | qwen3.5-flash | 439 ±147 | ~$0.27 | 7 | 2-4-1 | 29.7% | 29.3% | 57.1% | +1 | 69.6 | 7291 | 55s | 65.9% | | 200 | qwen2.5-turbo ˟ | 438 ±134 | ~$0.02 | 10 | 0-10-0 | 31.7% | 27.9% | 50% | +3.2 | 95.9 | 438 | 3.8s | 40.1% | | 201 | glm-4.6 | 437 ±135 | ~$0.84 | 10 | 0-9-1 | 31.4% | 26.2% | 45% | +2 | 76.5 | 2759 | 30s | 52.5% | | 202 | jamba-mini-1.7 | 428 ±163 | ~$0.29 | 5 | 0-5-0 | 33.7% | 35.2% | 50% | -4.2 | 134.8 | 1457 | 4.1s | 34.6% | | 203 | seed-1.6-flash | 427 ±155 | ~$0.25 | 6 | 0-5-1 | 34.4% | 26.7% | 41.7% | -13.2 | 55 | 5932 | 37s | 40.8% | | 204 | seed-1.6 | 425 ±154 | ~$0.19 | 6 | 0-5-1 | 35.2% | 23.2% | 41.7% | +5.2 | 52 | 791 | 21s | 46.9% | | 205 | qwen3.7-plus | 423 ±154 | ~$0.56 | 7 | 0-4-3 | 35.6% | 22.4% | 28.6% | -11 | 70.9 | 4076 | 75s | 80.6% | | 206 | mistral-medium-3.5 | 421 ±149 | $1.05 | 8 | 0-7-1 | 29.7% | 31.2% | 43.8% | -2.5 | 113.3 | 542 | 3.1s | 55.3% | | 207 | glm-4.6v | 420 ±130 | ~$0.55 | 10 | 0-10-0 | 29.9% | 30.2% | 50% | -3 | 101.7 | 2407 | 50s | 42.6% | | 208 | random-mover | 419 | - | 200 | 15-170-15 | 28.6% | 30.5% | 50% | 0 | 174.2 | - | - | 100% | | 209 | qwen3-coder-next | 416 ±165 | ~$0.07 | 5 | 0-5-0 | 28.4% | 33.8% | 50% | +2.8 | 68.8 | 366 | 4.2s | 46.6% | | 210 | qwen2.5-max ˟ | 414 ±147 | ~$0.94 | 8 | 0-7-1 | 29.3% | 23.9% | 43.8% | -1 | 95.4 | 563 | 8.1s | 45.5% | | 211 | mistral-small-4-119b-a6b | 411 ±147 | ~$0.11 | 7 | 1-6-0 | 26.4% | 27.4% | 57.1% | +4.1 | 119 | 520 | 3.5s | 41.2% | | 212 | qwen3-32b | 409 ±152 | ~$0.32 | 7 | 0-5-2 | 34.2% | 26.9% | 35.7% | -7 | 77.9 | 3684 | 85s | 40.1% | | 213 | qwen3-coder-plus | 408 ±159 | ~$0.16 | 6 | 0-4-2 | 32.9% | 26.5% | 33.3% | -5.8 | 52.8 | 327 | 5.9s | 53.3% | | 214 | mistral-medium-3 | 404 ±127 | ~$0.24 | 11 | 0-10-1 | 32% | 29.7% | 45.5% | +0.2 | 92.5 | 582 | 7.3s | 55.1% | | 215 | command-a | 403 ±151 | ~$1.55 | 7 | 0-6-1 | 30.2% | 29.3% | 42.9% | -1.9 | 109.1 | 504 | 5.0s | 45.9% | | 216 | mistral-medium-3.1 | 402 ±135 | ~$0.22 | 10 | 0-8-2 | 32.3% | 29.6% | 40% | -12.4 | 94.7 | 448 | 5.6s | 47.2% | | 217 | claude-3-haiku ˟ | 384 ±162 | ~$0.48 | 5 | 0-5-0 | 27.4% | 30% | 50% | -2.4 | 158.4 | 781 | 2.4s | 40.4% | | 218 | kimi-linear-48b-a3b-instruct | 384 ±162 | ~$0.32 | 5 | 0-5-0 | 27.1% | 26.7% | 50% | -1.6 | 148.8 | 829 | 2.8s | 32.6% | | 219 | command-r-plus-08-2024 | 380 ±162 | ~$2.60 | 5 | 0-5-0 | 26.4% | 33.5% | 50% | +2.6 | 123.8 | 696 | 12s | 43.1% | | 220 | qwen3-235b-a22b-instruct-2507 | 368 ±136 | ~$0.05 | 11 | 0-5-6 | 32.6% | 36.4% | 22.7% | -5.2 | 68.2 | 479 | 6.6s | 62.9% |