SuperCLUE General (September 2025) - Precise Instruction Following: leaderboard
Metric: Score. Source: www.superclueai.com. 37 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 (High) | 73.53 |
| 2 | GPT-5 (High) | 73.26 |
| 3 | Claude Sonnet 4.5 (Thinking) | 69.25 |
| 4 | Gemini 3 Pro (Preview) | 68.45 |
| 5 | O3 (High) | 67.91 |
| 6 | O4 Mini (High) | 67.65 |
| 7 | Claude Opus 4.1 (Thinking) | 63.1 |
| 8 | Qwen 3 Next 80B A3B (Thinking) | 56.95 |
| 9 | DeepSeek V3.2 Exp (Thinking) | 55.61 |
| 10 | DeepSeek V3.1 Terminus (Thinking) | 54.81 |
| 11 | Qwen 3 235B A22B 2507 (Thinking) | 51.6 |
| 12 | GPT-OSS-120B | 50 |
| 13 | Gemini 2.5 Pro | 49.73 |
| 14 | Kimi K2 (Thinking) | 48.93 |
| 15 | Hunyuan-T1-20250822 | 45.45 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-september-2025-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-09-19.