SuperCLUE General (May 2025) - Text Understanding and Creation: leaderboard
Metric: Score. Source: www.superclueai.com. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-thinking-pro-250415 | 81.04 |
| 2 | Claude Opus 4 (Thinking) | 80.62 |
| 3 | SenseNova V6 Reasoner | 80.43 |
| 4 | Gemini 2.5 Pro (Preview 05-06) | 80.15 |
| 5 | DeepSeek V3 (0324) | 80.04 |
| 6 | Qwen 3 32B (Thinking) | 79.7 |
| 7 | O3 | 79.67 |
| 8 | DeepSeek R1 | 79.57 |
| 9 | ERNIE-X1-Turbo-32K | 79.37 |
| 10 | Gemini 2.5 Flash (Preview 04-17) | 79.26 |
| 11 | Gemini 2.5 Flash (Preview 05-20) | 79.18 |
| 12 | Step 2 16K | 78.76 |
| 13 | O4 Mini (High) | 77.75 |
| 14 | Gemma 3 27B (IT) | 77.72 |
| 15 | Gemma 3 12B (IT) | 75.96 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-may-2025-text-understanding-and-creation · How It Works · Data refreshed daily, snapshot 2026-09-19.