Vals AI AIME — leaderboard
Metric: Accuracy (%). Source: www.vals.ai. 96 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 98.12 |
| 2 | GPT-5.2 | 96.88 |
| 3 | Muse Spark | 96.88 |
| 4 | Gemini 3 Pro (Preview) | 96.68 |
| 5 | GPT-5.4 (2026-03-05) | 96.67 |
| 6 | Grok 4.20 0309 (Reasoning) | 96.46 |
| 7 | Claude Opus 4.7 | 96.25 |
| 8 | Gemini 3 Flash (Preview) | 95.62 |
| 9 | GPT-5.4 Mini | 95.62 |
| 10 | Claude Opus 4.6 (Thinking) | 95.62 |
| 11 | Kimi K2.5 (Thinking) | 95.62 |
| 12 | Claude Opus 4.5 (20251101) (Thinking) | 95.42 |
| 13 | Qwen 3.6 Plus | 94.58 |
| 14 | GPT-5 | 93.37 |
| 15 | GPT-5.1 | 93.33 |
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-aime · How the rankings work · Data refreshed daily, snapshot 2026-07-22.