FanOutQA — leaderboard
Metric: Accuracy (%, closedbook loose). Source: fanoutqa.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Large 2 (Jul) | 47.45 |
| 2 | Mixtral 8x7B Instruct | 46.96 |
| 3 | Llama 3 70B Instruct | 46.62 |
| 4 | GPT-OSS-120B | 46.6 |
| 5 | GPT-4 Turbo | 45.97 |
| 6 | Mistral-Small-Instruct-2409 | 45.01 |
| 7 | Claude 3 Opus | 44.77 |
| 8 | GPT-4o | 44.12 |
| 9 | Llama 2 70B Chat | 44.03 |
| 10 | Mistral 7B Instruct | 42.71 |
| 11 | GPT-OSS-20B | 39.96 |
| 12 | GPT-3.5 Turbo | 39.8 |
| 13 | GPT-4 | 35.5 |
| 14 | Claude 2.1 | 34.09 |
| 15 | Gemma 1.1 7B (IT) | 18.65 |
Interactive version: theaggregate.ai/benchmark?slug=fanoutqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.