SuperCLUE General (2025 Annual) - Agentic Task Planning: leaderboard
SuperCLUE general leaderboard, 2025 Annual edition (2025年度测评): agentic task planning (智能体任务规划) score from the 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: Around February 2027. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 (High) | 81.39 | #115 (GPT-5.2) |
| 2 | Doubao-Seed-2.0-Pro-260215 | 77.78 | #86 |
| 3 | Claude Opus 4.6 (High) | 77.52 | #67 (Claude Opus 4.6) |
| 4 | Claude Opus 4.5 (Thinking) | 74.87 | #87 (Claude Opus 4.5) |
| 5 | Gemini 3.1 Pro (Preview) (High) | 71.03 | #64 (Gemini 3.1 Pro (Preview)) |
| 6 | Qwen 3 Max (Thinking) | 70.13 | #213 (Qwen 3 Max) |
| 7 | Qwen 3.5 397B A17B (Thinking) | 68.92 | #154 (Qwen 3.5 397B A17B) |
| 8 | Kimi K2.5 (Thinking) | 68.06 | #152 (Kimi K2.5) |
| 9 | Gemini 3 Pro (Preview) | 65.02 | #71 |
| 10 | Qwen 3 Max (Preview) (Thinking) | 64.4 | #248 (Qwen 3 Max (Preview)) |
| 11 | GLM-5 | 62.12 | #149 |
| 12 | Kimi K2 (Thinking) | 59.01 | #252 (Kimi K2) |
| 13 | Qwen 3.5 122B A10B (Thinking) | 56.5 | #184 (Qwen 3.5 122B A10B) |
| 14 | Qwen 3.5 27B (Thinking) | 56.14 | #192 (Qwen 3.5 27B) |
| 15 | GLM-4.7 | 56.03 | #202 |
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-2025-annual-agentic-task-planning · How It Works · Data refreshed daily, snapshot 2026-11-05.