math benchmark
HMMT Feb 26 Leaderboard
HMMT Feb 26 is a math competition benchmark based on problems from the Harvard-MIT Mathematics Tournament.
Updated Sep 5, 2026
Models12
Model coverage12
MetricScore
EvidenceB
HMMT Feb 26 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score97.10% | Percentile100.00% | Participants12 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Score95.20% | Percentile90.91% | Participants12 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score94.80% | Percentile81.82% | Participants12 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score92.90% | Percentile72.73% | Participants12 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score92.70% | Percentile63.64% | Participants12 | EvidenceC | Evaluated |
| Rank06 | ModelZA | Score92.50% | Percentile54.55% | Participants12 | EvidenceC | Evaluated |
| Rank07 | ModelDE | Score91.90% | Percentile45.45% | Participants12 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score87.80% | Percentile36.36% | Participants12 | EvidenceC | Evaluated |
| Rank09 | ModelMI | Score84.90% | Percentile27.27% | Participants12 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score84.30% | Percentile18.18% | Participants12 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score83.60% | Percentile9.09% | Participants12 | EvidenceC | Evaluated |
| Rank12 | ModelZA | Score82.60% | Percentile0.00% | Participants12 | EvidenceC | Evaluated |
HMMT Feb 26 Highlights
The leading models and scores on this benchmark.
HMMT Feb 26 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for HMMT Feb 26
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is HMMT Feb 26?
What HMMT Feb 26 measures and how its scores work.
HMMT Feb 26 is a benchmark based on problems from the Harvard-MIT Mathematics Tournament.
It measures advanced mathematical problem-solving and reasoning using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- HMMT Feb 26
- 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 HMMT Feb 26.
Which model scores highest on HMMT Feb 26?
Qwen3.7 Max is currently ranked first with 97.10%.
What are the top three models on HMMT Feb 26?
The current leaders are Qwen3.7 Max (97.10%), DeepSeek-V4-Pro-Max (95.20%), and DeepSeek-V4-Flash-Max (94.80%).
Which HMMT Feb 26 model has the lowest official input price?
DeepSeek-V4-Flash-Max has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among HMMT Feb 26 results?
The fastest matched records are GLM-5.2 (3.96 tok/s via ZAI) and Kimi K2.6 (1.24 tok/s via Moonshot AI).
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.