AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
MATH (CoT)
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions. Each problem includes full step-by-step solutions and spans multiple difficulty levels (1-5) across seven mathematical subjects. This variant uses Chain-of-Thought prompting to encourage step-by-step reasoning.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 6
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Llama 3.1 70B Instruct | 0.68 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |
| Ministral 3 (14B Base 2512) | 0.676 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Mistral Large 3 | 0.676 | Not recorded | Not recorded | 2025-09-01 · model_announcement | LLM Stats |
| Ministral 3 (8B Base 2512) | 0.626 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Ministral 3 (3B Base 2512) | 0.601 | Not recorded | Not recorded | 2025-12-04 · model_announcement | LLM Stats |
| Llama 3.1 8B Instruct | 0.519 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |