OpenCompass Reasoning - Humanities - English (CompassBench 2411): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Mini (2024-09-12) | 76.5 |
| 2 | Yi Lightning | 67.8 |
| 3 | Grok Beta | 64.4 |
| 4 | Qwen 2.5 72B Instruct | 60.6 |
| 5 | DeepSeek V2.5 | 60.6 |
| 6 | GPT-4o (2024-11-20) | 59 |
| 7 | GLM-4 Plus | 58.4 |
| 8 | Mistral Large 2 (Nov) Instruct (2411) | 58.1 |
| 9 | TeleChat2 | 57.5 |
| 10 | Step 2 16K | 51.5 |
| 11 | Yi 1.5 34B Chat | 51.1 |
| 12 | GPT-4o (2024-08-06) | 50 |
| 13 | Ministral-8B-Instruct-2410 | 49.8 |
| 14 | Llama 3.1 70B Instruct | 49.2 |
| 15 | Qwen 2.5 7B Instruct | 48.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-reasoning-humanities-english-compassbench-2411 · How It Works · Data refreshed daily, snapshot 2026-09-19.