ObviousBench: leaderboard
Metric: Answer pass³ (%). Source: benchmarklist.com. 506 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 100 |
| 2 | GPT-5 (High) | 100 |
| 3 | GPT-5.5 (xHigh) | 100 |
| 4 | Gemini 3.5 Flash (High) | 100 |
| 5 | Grok 4.5 (High) | 100 |
| 6 | GPT-5 (Medium) | 100 |
| 7 | Gemini 3.1 Pro (Preview) (High) | 100 |
| 8 | Grok 4.6 (High) | 100 |
| 9 | GPT-5.5 (Medium) | 100 |
| 10 | Claude Opus 5 (High) | 100 |
| 11 | Hy3 (High) | 100 |
| 12 | Grok 4.6 (Medium) | 100 |
| 13 | Gemini 3.1 Pro (Preview) (Medium) | 100 |
| 14 | Qwen 3.5 397B A17B | 99.31 |
| 15 | Gemini 3.5 Flash | 99.31 |
Interactive version: theaggregate.ai/benchmark?slug=obviousbench · How It Works · Data refreshed daily, snapshot 2026-09-19.