Benchmark
MATH (CoT) Benchmark
What is MATH (CoT)?
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions. Each problem includes…
- Modality
- text
- Evaluates
- math, reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 6
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/math-%28cot%29?top_n=500
MATH (CoT) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Llama 3.1 70B Instruct | Meta | 0.68 | 2024-07-23 | evidence |
| Llama 3.1 8B Instruct | Meta | 0.519 | 2024-07-23 | evidence |
| Ministral 3 (14B Base 2512) | Mistral | 0.676 | 2025-12-04 | evidence |
| Ministral 3 (3B Base 2512) | Mistral | 0.601 | 2025-12-04 | evidence |
| Ministral 3 (8B Base 2512) | Mistral | 0.626 | 2025-12-04 | evidence |
| Mistral Large 3 | Mistral | 0.676 | 2025-09-01 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.