Harvard-MIT Mathematics Tournament February 2025 (HMMT Feb 2025)
We show this table for reference; we do not rank on it.
A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.
Benchmark score on HMMT Feb 2025 — November 13, 2026
We compile the HMMT Feb 2025 rows from provider self-reports and secondary reports. GLM-5 leads the table at 97.5%, followed by GLM-4.7 (97.1%) and Qwen3.6 Plus (96.7%). We do not use these results to rank models overall.
GLM-5
Z.AI
Another lab’s comparison tableGLM-4.7
Z.AI
Reported by Z.AIQwen3.6 Plus
Alibaba
Reported by Alibaba15 modelsMathematicsCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (15 models)
None of the 15 results on this page has a documented run by the benchmark or an independent evaluator: 13 reported by the labs that built the models and 2 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | GLM-5Z.AIAnother lab’s comparison table | 97.5% | Another lab’s comparison table | Not reported | Open |
| 2 | GLM-4.7Z.AIReported by Z.AI | 97.1% | Reported by Z.AI | Not reported | Open |
| 3 | Qwen3.6 PlusAlibabaReported by Alibaba | 96.7% | Reported by Alibaba | Not reported | Closed |
| 4 | Kimi K2.5 (Reasoning)Moonshot AIReported by Moonshot AI | 95.4% | Reported by Moonshot AI | Not reported | Open |
| 5 | Kimi K2.5Moonshot AIReported by Moonshot AI | 95.4% | Reported by Moonshot AI | Not reported | Open |
| 6 | Qwen3.5 397BAlibabaReported by Alibaba | 94.8% | Reported by Alibaba | Not reported | Open |
| 7 | Qwen3.6-27BAlibabaReported by Alibaba | 93.8% | Reported by Alibaba | Not reported | Open |
| 8 | Nemotron 3 Super 100BNVIDIAReported by NVIDIA | 93.7% | Reported by NVIDIA | Not reported | Open |
| 9 | Claude Opus 4.5AnthropicAnother lab’s comparison table | 92.9% | Another lab’s comparison table | Not reported | Closed |
| 10 | Qwen3.6-35B-A3BAlibabaReported by Alibaba | 90.7% | Reported by Alibaba | Not reported | Open |
| 11 | Granite 4.2 30BIBMReported by IBM | 89.2% | Reported by IBM | Not reported | Open |
| 12 | Sarvam 105BSarvamReported by Sarvam | 85.8% | Reported by Sarvam | Not reported | Open |
| 13 | Granite 4.2 8BIBMReported by IBM | 78.3% | Reported by IBM | Not reported | Open |
| 14 | Sarvam 30BSarvamReported by Sarvam | 73.3% | Reported by Sarvam | Not reported | Open |
| 15 | Granite 4.2 3BIBMReported by IBM | 66.7% | Reported by IBM | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Among the reported HMMT Feb 2025 rows, GLM-5 is first at 97.5%. The third row is 0.8 points behind. The broader top-10 range is 6.8 points, so many of the published results sit in a relatively narrow band.
15 models have been evaluated on HMMT Feb 2025. The benchmark falls in the Mathematics category. HMMT Feb 2025 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About HMMT Feb 2025
Year
2025
Tasks
Competition math problems
Format
Contest mathematics
Difficulty
Olympiad-style mathematics
BenchLM stores this HMMT monthly slice separately from the aggregate HMMT rows so first-party exact values remain visible without overwriting the broader yearly HMMT reference.
Freshness and provenance
Version
HMMT Feb 2025 2025
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does HMMT Feb 2025 measure?
A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.
Which model scores highest on HMMT Feb 2025?
GLM-5 by Z.AI currently leads with a score of 97.5% on HMMT Feb 2025.
How many models are evaluated on HMMT Feb 2025?
15 AI models have published results on HMMT Feb 2025 in the BenchLM catalog.
Compare top models on HMMT Feb 2025
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.