SuperCLUE General (March 2026) - Agentic Task Planning: leaderboard
SuperCLUE general leaderboard, March 2026 edition (2026年3月): 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. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (Max) | 89.35 | #67 (Claude Opus 4.6) |
| 2 | Doubao-Seed-2-0-Pro-260215 (High) | 81.04 | |
| 3 | GPT-5.4 (xHigh) | 80.04 | #83 (GPT-5.4) |
| 4 | Gemini 3.1 Pro (Preview) (High) | 78.96 | #64 (Gemini 3.1 Pro (Preview)) |
| 5 | Kimi K2.5 (Thinking) | 78.44 | #152 (Kimi K2.5) |
| 6 | DeepSeek V4 Pro (Max) | 77.49 | #112 (DeepSeek V4 Pro) |
| 7 | DeepSeek V4 Flash (Max) | 75.28 | #155 (DeepSeek V4 Flash) |
| 8 | Qwen 3.5 397B A17B (Thinking) | 71.52 | #154 (Qwen 3.5 397B A17B) |
| 9 | LongCat-Flash-Thinking-2601 | 67.94 | #242 |
| 10 | Grok 4.20 Beta (0309) (Reasoning) | 67.35 | #198 (Grok 4.20 Beta (0309)) |
| 11 | GLM-5 | 66.64 | #149 |
| 12 | MiniMax-M2.5 | 65.64 | #316 |
| 13 | Qwen 3.5 122B A10B (Thinking) | 65.15 | #184 (Qwen 3.5 122B A10B) |
| 14 | Step 3.5 Flash | 64.06 | #281 |
| 15 | Gemini 3 Flash (Preview) (High) | 63.65 | #90 (Gemini 3 Flash (Preview)) |
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-march-2026-agentic-task-planning · How It Works · Data refreshed daily, snapshot 2026-11-05.