AidanBench — leaderboard
Metric: Novel Answers. Source: aidanbench.com. 56 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 | 6054 |
| 2 | O3 Mini (High) | 4921 |
| 3 | O3 Mini (Medium) | 3368 |
| 4 | Gemini 2.5 Pro (Preview 03-25) | 3211 |
| 5 | GPT-4.5 (Preview) | 3003 |
| 6 | Claude 3.5 Sonnet | 2671 |
| 7 | O3 Mini (Low) | 2300 |
| 8 | Grok 3 Mini Beta | 2284 |
| 9 | Claude 3.7 Sonnet (Thinking) | 2170 |
| 10 | Gemma 3 27B (IT) | 2028 |
| 11 | Claude 3.7 Sonnet | 1906 |
| 12 | O1 Preview | 1875 |
| 13 | Gemini 2.0 Flash (Preview) | 1872 |
| 14 | Grok 3 | 1795 |
| 15 | Gemma 3 12B (IT) | 1785 |
Interactive version: aibenchmarks.dev/benchmark?slug=aidanbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.