math benchmark
MATH (CoT) Leaderboard
MATH (CoT) is a benchmark based on 12,500 challenging competition mathematics problems using Chain-of-Thought prompting to encourage step-by-step reasoning.
Updated Sep 5, 2026
Models6
Model coverage6
MetricScore
EvidenceB
MATH (CoT) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score68.00% | Percentile100.00% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score67.60% | Percentile80.00% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score67.60% | Percentile60.00% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score62.60% | Percentile40.00% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score60.10% | Percentile20.00% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelME | Score51.90% | Percentile0.00% | Participants6 | EvidenceC | Evaluated |
MATH (CoT) Highlights
The leading models and scores on this benchmark.
MATH (CoT) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MATH (CoT)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MATH (CoT)?
What MATH (CoT) measures and how its scores work.
MATH (CoT) is a Chain-of-Thought variant of the MATH dataset, which contains problems from AMC 10, AMC 12, AIME, and other mathematics competitions across seven mathematical subjects and difficulty levels 1-5.
It measures Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MATH (CoT)
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MATH (CoT).
Which model scores highest on MATH (CoT)?
Llama 3.1 70B Instruct is currently ranked first with 68.00%.
What are the top three models on MATH (CoT)?
The current leaders are Llama 3.1 70B Instruct (68.00%), Ministral 3 (14B Base 2512) (67.60%), and Mistral Large 3 (67.60%).
Which MATH (CoT) model has the lowest official input price?
Ministral 3 (14B Base 2512) has the lowest matched official input price at $0.10 input / $0.10 output per 1M tokens.
Which models are fastest among MATH (CoT) results?
The fastest matched records are Llama 3.1 8B Instruct (2,047.00 tok/s via Cerebras) and Llama 3.1 70B Instruct (1,204.00 tok/s via Cerebras).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.