SuperCLUE General (July 2025) - Precise Instruction Following: leaderboard
Metric: Score. Source: www.superclueai.com. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (High) | 66.77 |
| 2 | O3 (High) | 64.09 |
| 3 | O4 Mini (High) | 59.64 |
| 4 | DeepSeek V3.1 (Thinking) | 47.18 |
| 5 | Claude Opus 4 (Thinking) | 44.81 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 43.62 |
| 7 | Hunyuan-T1-20250711 | 42.73 |
| 8 | GPT-OSS-120B | 41.25 |
| 9 | Gemini 2.5 Pro | 39.76 |
| 10 | GPT-OSS-20B | 35.31 |
| 11 | DeepSeek R1 0528 | 35.31 |
| 12 | Gemini 2.5 Flash | 34.12 |
| 13 | Doubao-Seed-1.6-thinking-250715 | 32.34 |
| 14 | Grok 4 | 29.97 |
| 15 | GLM-4.5 | 27.22 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-july-2025-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-09-19.