LLM Benchmark Table
🌙
Toggle Dark Mode
Sort by clicking table headers
FAQ
Q: What does "TOTAL" mean?
A: Total represents the sum of all test cases processed by the model.
Q: What is $mToK?
A: mToK stands for cost per million tokens processed in USD.
Q: What do the Reason, STEM, Code etc. columns indicate?
A: These are boolean flags indicating model capabilities or performance in specific domains.