SuperCLUE General (May 2025) - Precise Instruction Following: leaderboard
SuperCLUE general leaderboard, May 2025 edition (2025年5月): precise instruction following (精确指令遵循) score (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: Estimated already saturated. 40 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O4 Mini (High) | 68.07 | #185 (O4 Mini) |
| 2 | O3 | 66.95 | #132 |
| 3 | Claude Opus 4 (Thinking) | 59.1 | #170 (Claude Opus 4) |
| 4 | Gemini 2.5 Pro (Preview 05-06) | 53.78 | #156 |
| 5 | Gemini 2.5 Flash (Preview 05-20) | 41.18 | #229 |
| 6 | Doubao-1.5-thinking-pro-250415 | 35.29 | #226 |
| 7 | Gemini 2.5 Flash (Preview 04-17) | 34.73 | #246 |
| 8 | SenseNova V6 Reasoner | 31.93 | #317 |
| 9 | DeepSeek R1 | 31.37 | #262 |
| 10 | Llama 4 Maverick Instruct | 30.81 | #467 |
| 11 | DeepSeek V3 (0324) | 30.25 | #349 |
| 12 | Llama 3.3 70B Instruct | 27.73 | #541 |
| 13 | Qwen 3 32B (Thinking) | 26.61 | #449 (Qwen 3 32B) |
| 14 | Qwen 3 30B A3B (Thinking) | 26.33 | #496 (Qwen 3 30B A3B) |
| 15 | Qwen 3 235B A22B (Thinking) | 26.05 | #323 (Qwen 3 235B A22B) |
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-may-2025-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-05.