OpenCompass LLM - Language - Chinese (CompassBench 2507): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 28 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-Seed-1.6-thinking-250715 | 86.8 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 84.3 |
| 3 | GPT-5 | 83.4 |
| 4 | Grok 4 | 81.4 |
| 5 | DeepSeek R1 0528 | 80.5 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 80.3 |
| 7 | Gemini 2.5 Pro | 78.7 |
| 8 | GLM 4.5 Air | 77.1 |
| 9 | Gemma 3 27B (IT) | 75.8 |
| 10 | O4 Mini (2025-04-16) (High) | 75.8 |
| 11 | ERNIE-X1-Turbo-32K | 75.5 |
| 12 | DeepSeek V3 (0324) | 75.1 |
| 13 | O3 (2025-04-16) (High) | 75.1 |
| 14 | GLM-4.5 | 74.7 |
| 15 | Hunyuan-T1-20250711 | 74.6 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-language-chinese-compassbench-2507 · How It Works · Data refreshed daily, snapshot 2026-09-19.