OpenCompass Language - Instruction Following - 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 | 84.8 |
| 2 | Hunyuan-T1-20250711 | 83.1 |
| 3 | DeepSeek R1 0528 | 81.2 |
| 4 | ERNIE-X1-Turbo-32K | 81 |
| 5 | Hunyuan A13B-Instruct | 79.6 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 79.5 |
| 7 | Gemini 2.5 Pro | 79.4 |
| 8 | GPT-5 | 79 |
| 9 | Kimi K2 | 78.8 |
| 10 | Qwen 3 235B A22B 2507 Instruct | 78.7 |
| 11 | DeepSeek V3 (0324) | 76.8 |
| 12 | O3 (2025-04-16) (High) | 73.9 |
| 13 | GLM 4.5 Air | 73.7 |
| 14 | Grok 4 | 72.9 |
| 15 | MiniMax M1 80k | 72.4 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-instruction-following-chinese-compassbench-2507 · How It Works · Data refreshed daily, snapshot 2026-09-19.