OpenCompass LLM - Language - English (CompassBench 2411): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Yi Lightning | 61.2 |
| 2 | Grok Beta | 60.7 |
| 3 | GLM-4 Plus | 60.5 |
| 4 | O1 Mini (2024-09-12) | 60.3 |
| 5 | GPT-4o (2024-11-20) | 59.5 |
| 6 | TeleChat2 | 57.3 |
| 7 | DeepSeek V2.5 | 56.6 |
| 8 | Qwen 2.5 72B Instruct | 56.5 |
| 9 | Mistral Large 2 (Nov) Instruct (2411) | 55.3 |
| 10 | Step 2 16K | 55 |
| 11 | Yi 1.5 34B Chat | 53.7 |
| 12 | Llama 3.1 405B Instruct FP8 | 50.9 |
| 13 | Llama 3.1 70B Instruct | 50.4 |
| 14 | GPT-4o (2024-08-06) | 50 |
| 15 | Mistral-Small-Instruct-2409 | 50 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-language-english-compassbench-2411 · How It Works · Data refreshed daily, snapshot 2026-09-19.