AutoLogi: leaderboard
1,575 English and 883 Chinese open-ended logic puzzles generated automatically from AR-LSAT and LogiQA passages by Qwen Team and Fudan (2025); JSON answers checked by program verifiers, accuracy.
Metric: Score (imported). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-08-06) | 62.04 | #336 |
| 2 | Claude 3.5 Sonnet | 60.97 | #350 |
| 3 | Llama 3.1 405B Instruct | 59.42 | #457 |
| 4 | Llama 3.1 70B Instruct | 53.79 | #561 |
| 5 | Qwen 2.5 72B Instruct | 53.5 | #454 |
| 6 | Qwen 2.5 7B Instruct | 27.28 | #862 |
| 7 | Llama 3.1 8B Instruct | 25.53 | #1035 |
| 8 | GPT-3.5 Turbo | 18.93 | #865 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=autologi · How It Works · Data refreshed daily, snapshot 2026-10-20.