SuperCLUE-SWE (March 2026) - Overall: leaderboard
SuperCLUE-SWE resolves real GitHub issues from Chinese open-source projects with Chinese problem descriptions. March 2026 edition (2026年3月): headline 总分 of the 总榜单 sheet. Each dated workbook is a separate evaluation round, kept apart from the current board. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around 2028. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (Max) | 50 | #67 (Claude Opus 4.6) |
| 2 | Kimi K2.5 (Thinking) | 40 | #152 (Kimi K2.5) |
| 3 | Gemini 3.1 Pro (Preview) (High) | 40 | #64 (Gemini 3.1 Pro (Preview)) |
| 4 | Gemini 3 Flash (Preview) (High) | 36.67 | #90 (Gemini 3 Flash (Preview)) |
| 5 | Doubao-Seed-2-0-Pro-260215 (High) | 36.67 | |
| 6 | DeepSeek V3.2 (Thinking) | 33.33 | #210 (DeepSeek V3.2) |
| 7 | MiMo-V2-Pro | 33.33 | #177 |
| 8 | Grok 4.20 Beta (0309) (Reasoning) | 33.33 | #198 (Grok 4.20 Beta (0309)) |
| 9 | Tencent HY 2.0 Think | 33.33 | #206 |
| 10 | MiniMax-M2.5 | 30 | #316 |
| 11 | Qwen 3.5 122B A10B (Thinking) | 30 | #184 (Qwen 3.5 122B A10B) |
| 12 | GLM-5 | 26.67 | #149 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-swe-march-2026-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.