SuperCLUE General (May 2025) - Precise Instruction Following: leaderboard
Metric: Score. Source: www.superclueai.com. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini (High) | 68.07 |
| 2 | O3 | 66.95 |
| 3 | Claude Opus 4 (Thinking) | 59.1 |
| 4 | Gemini 2.5 Pro (Preview 05-06) | 53.78 |
| 5 | Gemini 2.5 Flash (Preview 05-20) | 41.18 |
| 6 | Doubao-1.5-thinking-pro-250415 | 35.29 |
| 7 | Gemini 2.5 Flash (Preview 04-17) | 34.73 |
| 8 | SenseNova V6 Reasoner | 31.93 |
| 9 | DeepSeek R1 | 31.37 |
| 10 | Llama 4 Maverick Instruct | 30.81 |
| 11 | DeepSeek V3 (0324) | 30.25 |
| 12 | Llama 3.3 70B Instruct | 27.73 |
| 13 | Qwen 3 32B (Thinking) | 26.61 |
| 14 | Kimi K1.5 | 25.77 |
| 15 | Gemma 3 27B (IT) | 20.45 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2025-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-09-19.