SuperCLUE General (March 2025) - Precise Instruction Following: leaderboard
Metric: Score. Source: www.superclueai.com. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini (High) | 66.4 |
| 2 | Claude 3.7 Sonnet | 48.92 |
| 3 | Doubao-1.5-pro-32k-250115 | 46.77 |
| 4 | hunyuan-turbos-20250226 | 41.13 |
| 5 | DeepSeek R1 | 39.52 |
| 6 | GPT-4.5 (Preview) | 35.75 |
| 7 | Gemini 2.0 Pro (Preview 02-05) | 33.6 |
| 8 | Gemini 2.0 Flash (01-21) (Thinking) | 33.6 |
| 9 | QwQ-32B | 29.92 |
| 10 | Llama 3.3 70B Instruct | 26.08 |
| 11 | DeepSeek V3 | 23.39 |
| 12 | DeepSeek R1 Distill Qwen 32B | 23.18 |
| 13 | Qwen 2.5 72B Instruct | 22.91 |
| 14 | GLM-4 Plus | 21.77 |
| 15 | GPT-4o Mini | 20.43 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-march-2025-precise-instruction-following · How It Works · Data refreshed daily, snapshot 2026-09-19.