SuperCLUE General (2025 Annual) - Precise Instruction Following: leaderboard
SuperCLUE general leaderboard, 2025 Annual edition (2025年度测评): precise instruction following (精确指令遵循) score from the 总排行榜 sheet. SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around February 2027. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 53.7 | #64 (Gemini 3.1 Pro (Preview)) |
| 2 | Claude Opus 4.6 (High) | 51.78 | #67 (Claude Opus 4.6) |
| 3 | Claude Opus 4.5 (Thinking) | 51.1 | #87 (Claude Opus 4.5) |
| 4 | Gemini 3 Pro (Preview) | 43.56 | #71 |
| 5 | Doubao-Seed-2.0-Pro-260215 | 43.01 | #86 |
| 6 | Gemini 3 Flash (Preview) | 39.45 | #90 |
| 7 | GPT-5.2 (High) | 37.81 | #115 (GPT-5.2) |
| 8 | ERNIE 5.0 | 37.53 | #243 |
| 9 | DeepSeek V3.2 (Thinking) | 29.86 | #210 (DeepSeek V3.2) |
| 10 | Qwen 3 Max (Thinking) | 28.22 | #213 (Qwen 3 Max) |
| 11 | GLM-5 | 27.35 | #149 |
| 12 | GPT-OSS-120B (High) | 25.75 | #346 (GPT-OSS-120B) |
| 13 | Qwen 3 Max (Preview) (Thinking) | 24.66 | #248 (Qwen 3 Max (Preview)) |
| 14 | Kimi K2.5 (Thinking) | 24.45 | #152 (Kimi K2.5) |
| 15 | Qwen 3.5 27B (Thinking) | 22.19 | #192 (Qwen 3.5 27B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-2025-annual-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-05.