CMT-Benchmark
Progress Over Time
Interactive timeline showing model performance evolution on CMT-Benchmark
CMT-Benchmark Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Tencent | 295B | — | — |
What is CMT-Benchmark?
CMT-Benchmark evaluates models on condensed matter theory problems, testing advanced physics reasoning across areas such as many-body systems, quantum field theory, and statistical mechanics.
CMT-Benchmark is a text benchmark evaluating models on physics, reasoning, and science tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.4.
Compare leaders on the best AI for physics, best AI for reasoning and best AI for science leaderboards.
Current leaders
Hy3 from Tencent currently leads the CMT-Benchmark leaderboard with a score of 0.379 across 1 evaluated AI models.
FAQ
Common questions about the CMT-Benchmark benchmark and leaderboard.