SuperCLUE General (July 2025) - Agent: leaderboard
SuperCLUE general leaderboard, July 2025 edition (2025年7月): agent (智能体Agent) score (总排行榜 sheet). SuperCLUE's periodic Chinese-language general evaluation uses a new question set each edition, so editions are separate boards. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Estimated already saturated. 47 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-Seed-1.6-thinking-250715 | 90.67 | #169 |
| 2 | O4 Mini (High) | 86.36 | #185 (O4 Mini) |
| 3 | DeepSeek V3.1 (Thinking) | 86.19 | #275 (DeepSeek V3.1) |
| 4 | Grok 4 | 83.71 | #189 |
| 5 | GLM-4.5 | 83.58 | #283 |
| 6 | SenseNova V6 Reasoner | 83.58 | #317 |
| 7 | GPT-5 (High) | 83.21 | #105 (GPT-5) |
| 8 | Qwen 3 235B A22B (Thinking) | 83.21 | #323 (Qwen 3 235B A22B) |
| 9 | Gemini 2.5 Pro | 82.09 | #159 |
| 10 | Gemini 2.5 Flash | 82.09 | #255 |
| 11 | DeepSeek R1 0528 | 82.09 | #232 |
| 12 | DeepSeek V3 (0324) | 81.34 | #349 |
| 13 | Qwen 3 235B A22B 2507 Instruct | 80.97 | #315 |
| 14 | Claude Opus 4 (Thinking) | 80.6 | #170 (Claude Opus 4) |
| 15 | Step 2 16K | 78.73 | #442 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-july-2025-agent · How It Works · Data refreshed daily, snapshot 2026-11-05.