HMMT 2025 — leaderboard
MathArena evaluation based on Harvard-MIT Mathematics Tournament 2025 problems, emphasizing olympiad-style high-school contest reasoning.
Metric: Score (self-reported). Source: matharena.ai. Status: saturated. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 OpenAI | 100 |
| 2 | Step 3.5 Flash StepFun | 98.33 |
| 3 | DeepSeek V3.2 Speciale DeepSeek | 97.5 |
| 4 | Gemini 3 Flash Preview Google | 97.5 |
| 5 | Gemini 3 Google | 97.5 |
| 6 | GLM 5 Z.ai | 97.5 |
| 7 | Claude Opus 4.8 | 96.5 |
| 8 | GPT-5.5 | 96.5 |
| 9 | Qwen3.7 Max max | 95 |
| 10 | Grok 4 xAI | 95 |
Interactive version: theaggregate.ai/benchmark?slug=hmmt-2025 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.