ErdosBench — leaderboard
Metric: Judge Average (0-4). Source: www.ulam.ai. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (xHigh) | 3.12 |
| 2 | GPT-5.5 (xHigh) | 2.68 |
| 3 | Kimi K2.7 Code | 2.62 |
| 4 | Claude Opus 4.8 (Max) | 2.51 |
| 5 | GLM-5.2 | 2.4 |
| 6 | Qwen 3.7 Max | 2.37 |
| 7 | MiniMax-M3 | 2.11 |
Interactive version: aibenchmarks.dev/benchmark?slug=erdosbench · How the rankings work · Data refreshed daily, snapshot 2026-07-20.