# HMMT Feb 2025 leaderboard

Mathematics benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/math-hmmt-feb2025

Harvard-MIT Mathematics Tournament February 2025. Every model the catalog carries a published HMMT Feb 2025 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Mathematics |
| Measure | Contest mathematics |
| Tasks | Competition math problems |
| Difficulty | Olympiad-style mathematics |
| Published by | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

A February 2025 HMMT slice used in exact-value provider tables for advanced contest-math reasoning.

## HMMT Feb 2025 ranking

16 models with a published HMMT Feb 2025 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Contest mathematics | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GLM-5](https://modelchoice.dev/models/glm-5) | Z.AI | 97.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GLM-4.7](https://modelchoice.dev/models/glm-4-7) | Z.AI | 97.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 96.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 95.4 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 95.4 | Last good 2026-11-18 · source benchlm:models |
| 6 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 94.8 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 93.8 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Nemotron 3 Super 100B](https://modelchoice.dev/models/nemotron-3-super-100b) | NVIDIA | 93.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 92.9 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 90.7 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Granite 4.2 30B](https://modelchoice.dev/models/granite-4-2-30b) | IBM | 89.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Sarvam 105B](https://modelchoice.dev/models/sarvam-105b) | Sarvam | 85.8 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Granite 4.2 8B](https://modelchoice.dev/models/granite-4-2-8b) | IBM | 78.3 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Sarvam 30B](https://modelchoice.dev/models/sarvam-30b) | Sarvam | 73.3 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Granite 4.2 3B](https://modelchoice.dev/models/granite-4-2-3b) | IBM | 66.7 | Observed 2026-11-21 · source benchlm:models |
| 16 | [DeepSeek-R1-0528-Qwen3-8B](https://modelchoice.dev/models/deepseek-r1-0528-qwen3-8b) | DeepSeek | 61.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
