math benchmark
HMMT 2025 Leaderboard
Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
Updated Aug 17, 2026
Models33
Model coverage33
MetricScore
EvidenceB
HMMT 2025 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score100.0% | Percentile100.0% | Participants33 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score99.4% | Percentile96.9% | Participants33 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score99.2% | Percentile93.8% | Participants33 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score97.5% | Percentile90.6% | Participants33 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score96.7% | Percentile87.5% | Participants33 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score95.4% | Percentile84.4% | Participants33 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score94.8% | Percentile81.3% | Participants33 | EvidenceC | Evaluated |
| Rank08 | ModelNV | Score94.7% | Percentile78.1% | Participants33 | EvidenceC | Evaluated |
| Rank09 | ModelZA | Score94.4% | Percentile75.0% | Participants33 | EvidenceC | Evaluated |
| Rank10 | ModelZA | Score94.0% | Percentile71.9% | Participants33 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score93.8% | Percentile68.8% | Participants33 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score93.3% | Percentile65.6% | Participants33 | EvidenceC | Evaluated |
| Rank13 | ModelXA | Score93.3% | Percentile62.5% | Participants33 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score92.0% | Percentile59.4% | Participants33 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score91.4% | Percentile56.3% | Participants33 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score90.7% | Percentile53.1% | Participants33 | EvidenceC | Evaluated |
| Rank17 | ModelDE | Score90.2% | Percentile50.0% | Participants33 | EvidenceC | Evaluated |
| Rank18 | ModelDE | Score90.2% | Percentile46.9% | Participants33 | EvidenceC | Evaluated |
| Rank19 | ModelAC | Score89.0% | Percentile43.8% | Participants33 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score87.8% | Percentile40.6% | Participants33 | EvidenceC | Evaluated |
| Rank21 | ModelSA | Score85.8% | Percentile37.5% | Participants33 | EvidenceC | Evaluated |
| Rank22 | ModelXI | Score84.4% | Percentile34.4% | Participants33 | EvidenceC | Evaluated |
| Rank23 | ModelDE | Score83.6% | Percentile31.3% | Participants33 | EvidenceC | Evaluated |
| Rank24 | ModelAC | Score83.2% | Percentile28.1% | Participants33 | EvidenceC | Evaluated |
| Rank25 | ModelDE | Score79.4% | Percentile25.0% | Participants33 | EvidenceC | Evaluated |
| Rank26 | ModelOP | Score75.6% | Percentile21.9% | Participants33 | EvidenceC | Evaluated |
| Rank27 | ModelAC | Score74.0% | Percentile18.8% | Participants33 | EvidenceC | Evaluated |
| Rank28 | ModelSA | Score73.3% | Percentile15.6% | Participants33 | EvidenceC | Evaluated |
| Rank29 | ModelMA | Score38.8% | Percentile12.5% | Participants33 | EvidenceC | Evaluated |
| Rank30 | ModelMA | Score38.8% | Percentile9.4% | Participants33 | EvidenceC | Evaluated |
| Rank31 | ModelOP | Score35.0% | Percentile6.3% | Participants33 | EvidenceC | Evaluated |
| Rank32 | ModelDE | Score33.5% | Percentile3.1% | Participants33 | EvidenceC | Evaluated |
| Rank33 | ModelOP | Score28.9% | Percentile0.0% | Participants33 | EvidenceC | Evaluated |
HMMT 2025 Highlights
The leading models and scores on this benchmark.
HMMT 2025 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for HMMT 2025
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis hmmt 2025 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01OPGPT-5.2 ProOpenAI
- Score
- 100.0%
- Price
- $21 input / $168 output per 1M tokens
- Speed
- Up to 25 tok/s via OpenAI
Strengths
- Ranks #1 of 33 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures HMMT 2025, not total model capability
- 02OPGPT-5.2OpenAI
- Score
- 99.4%
- Price
- $1.8 input / $14 output per 1M tokens
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #2 of 33 compared models
- 97th percentile on this benchmark
- C evidence result
Considerations
- This result measures HMMT 2025, not total model capability
- 03DEDeepSeek-V3.2-SpecialeDeepSeek
- Score
- 99.2%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 30 tok/s via DeepSeek
Strengths
- Ranks #3 of 33 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures HMMT 2025, not total model capability
- 04MAKimi K2-Thinking-0905Moonshot AI
- Score
- 97.5%
- Price
- $0.60 input / $2.5 output per 1M tokens
Strengths
- Ranks #4 of 33 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures HMMT 2025, not total model capability
- 05ACQwen3.6 PlusAlibaba Cloud / Qwen Team
- Score
- 96.7%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 16 tok/s via Together
Strengths
- Ranks #5 of 33 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures HMMT 2025, not total model capability
Selection summary
Best AI Models for HMMT 2025
GPT-5.2 Pro currently leads HMMT 2025 with 100.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is HMMT 2025?
What HMMT 2025 measures and how its scores work.
Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- HMMT 2025
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- hmmt-2025|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about HMMT 2025.
Which model scores highest on HMMT 2025?
GPT-5.2 Pro is currently ranked first with 100.0%.
What does HMMT 2025 measure?
Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
33 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.