MathDuels: leaderboard
MathDuels (2026) is a self-play mathematics benchmark: each model authors 30 hardened problems and solves those the other models wrote, with symbolic answer checking and a verifier removing ill-posed problems; ratings come from a Rasch model on an Elo-style scale. This board is the composite rating, the mean of the solver and author ratings, in rating points on an open scale; higher is better.
Metric: Composite rating (Elo-style points, open scale): the mean of the solver and author ratings; 19 models each author 30 hardened problems (six mathematical domains) and solve every problem authored by the others; answers checked symbolically, ill-posed problems removed by a GPT-5.4-high verifier; Rasch model on a shared rating scale anchored at Grok-4.1-fast-high = 1500, k = 30; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | High | 1919 | #99 |
| 2 | GPT-5.4 | High | 1870 | #135 |
| 3 | GPT-5.2 | High | 1737 | #185 |
| 4 | Claude Opus 4.6 | High | 1675 | #113 |
| 5 | Gemini 3 Flash | High | 1673 | #175 |
| 6 | Claude Sonnet 4.6 | High | 1593 | #173 |
| 7 | GPT-5.4 Mini | High | 1570 | #406 |
| 8 | Qwen 3.5 397B A17B | 1548 | #264 | |
| 9 | Kimi K2.5 | 1542 | #266 | |
| 10 | Grok 4.20 | High | 1485 | #301 |
| 11 | DeepSeek V3.2 | 1449 | #419 | |
| 12 | GLM-5 | 1438 | #269 | |
| 13 | MiniMax-M2.7 | 1372 | #539 | |
| 14 | Grok 4.1 Fast | High | 1335 | #427 |
| 15 | Step 3.5 Flash | 1328 | #526 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mathduels · How It Works · Data refreshed daily, snapshot 2026-11-21.