AGI-Eval Community - Subject Reasoning (English): leaderboard
Metric: Accuracy (%). Source: agi-eval.cn. 139 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 88.79 |
| 2 | GPT-5.5 | 87.52 |
| 3 | Claude Fable 5 | 87.32 |
| 4 | Claude Opus 4.6 | 87.21 |
| 5 | Gemini 3.5 Flash | 87.16 |
| 6 | Seed 2.0 Pro | 87.11 |
| 7 | Qwen 3.7 Max | 87.05 |
| 8 | Kimi K2.5 (Thinking) | 86.9 |
| 9 | Kimi K3 | 86.89 |
| 10 | Kimi K2.6 | 86.79 |
| 11 | Gemini 3 Pro (Preview) | 86.63 |
| 12 | Gemini 3.1 Pro (Preview) | 86.53 |
| 13 | Seed 2.1 Pro | 86.37 |
| 14 | GPT-5.1 | 86.16 |
| 15 | LongCat 2.0 | 85.95 |
Interactive version: theaggregate.ai/benchmark?slug=agi-eval-community-subject-reasoning-english · How It Works · Data refreshed daily, snapshot 2026-09-19.