SuperCLUE General (2025 Annual) - Agentic Task Planning: leaderboard
Metric: Score. Source: www.superclueai.com. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (High) | 81.39 |
| 2 | Doubao-Seed-2.0-Pro-260215 | 77.78 |
| 3 | Claude Opus 4.6 | 77.52 |
| 4 | Claude Opus 4.5 (Thinking) | 74.87 |
| 5 | Gemini 3.1 Pro (Preview) (High) | 71.03 |
| 6 | Qwen 3 Max (Thinking) | 70.13 |
| 7 | Qwen 3.5 397B A17B (Thinking) | 68.92 |
| 8 | Kimi K2.5 (Thinking) | 68.06 |
| 9 | Gemini 3 Pro (Preview) | 65.02 |
| 10 | Qwen 3 Max (Preview) (Thinking) | 64.4 |
| 11 | GLM-5 | 62.12 |
| 12 | Kimi K2 (Thinking) | 59.01 |
| 13 | Qwen 3.5 122B A10B (Thinking) | 56.5 |
| 14 | Qwen 3.5 27B (Thinking) | 56.14 |
| 15 | GLM-4.7 | 56.03 |
Interactive version: theaggregate.ai/benchmark?slug=superclue-general-2025-annual-agentic-task-planning · How It Works · Data refreshed daily, snapshot 2026-09-19.