AcuityBench — leaderboard
Metric: QA Exact (self-reported). Source: benchmarklist.com. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 85.3 |
| 2 | Gemini 2.5 Pro | 79.3 |
| 3 | GPT-5 Mini | 78 |
| 4 | GPT-5.4 | 77.2 |
| 5 | GPT-4.1 | 76.8 |
| 6 | Claude Sonnet 4.6 | 76.1 |
| 7 | DeepSeek V3.1 | 72.9 |
| 8 | Gemini 2.5 Flash | 70.8 |
| 9 | Claude Haiku 4.5 | 63 |
| 10 | Qwen 2.5 7B | 58.4 |
| 11 | Qwen 2.5 72B Instruct | 56.2 |
| 12 | Llama 3.3 70B Instruct | 53.3 |
Interactive version: theaggregate.ai/benchmark?slug=acuitybench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.