LLM Stats (AIME 2026): leaderboard
Problems from the 2026 American Invitational Mathematics Examination testing advanced math reasoning across algebra, combinatorics, number theory, and geometry.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.2 | 99.2 | #73 |
| 2 | Inkling | 97.1 | #126 |
| 3 | Kimi K2.6 | 96.4 | #104 |
| 4 | Inkling Small | 95.5 | #138 |
| 5 | Qwen 3.6 Plus | 95.3 | #120 |
| 6 | GLM-5.1 | 95.3 | #97 |
| 7 | Solar Pro 4 | 95.3 | #215 |
| 8 | Muse Glimmer 30B | 94.7 | #178 |
| 9 | Seed 2.0 Pro | 94.2 | #118 |
| 10 | Qwen 3.6 27B | 94.1 | #170 |
| 11 | Qwen 3 Max (Thinking) | 93.3 | #208 (Qwen 3 Max) |
| 12 | Ling-3.0-flash | 93.2 | #206 |
| 13 | Qwen 3.6 35B A3B | 92.7 | #226 |
| 14 | EXAONE 4.5 33B | 92.6 | #396 |
| 15 | Qwen 3.5 397B A17B | 91.3 | #146 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-aime-2026 · How It Works · Data refreshed daily, snapshot 2026-10-20.