physics benchmark
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.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
CMT-Benchmark leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | TE | 37.9% | 100.0% | 1 | C |
CMT-Benchmark highlights
The top published results on this benchmark's own scale.
What is CMT-Benchmark?
Definition and scoring fields from the benchmark registry.
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.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CMT-Benchmark
- Modality
- text
- Primary category
- physics
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- cmt-benchmark|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CMT-Benchmark.
Which model scores highest on CMT-Benchmark?
Hy3 is currently ranked first with 37.9%.
What does CMT-Benchmark measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.