Multi-SWE-bench mini (MopenHands): leaderboard
Metric: Resolved rate (%). Source: multi-swe-bench.github.io. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 18.25 |
| 2 | Gemini 2.5 Pro (Preview 03-25) | 18 |
| 3 | Claude 3.5 Sonnet (20241022) | 12.25 |
| 4 | DeepSeek V3 | 7.5 |
| 5 | DeepSeek R1 | 7 |
| 6 | GPT-4o (2024-11-20) | 6.75 |
| 7 | O3 Mini (2025-01-31) (High) | 5.75 |
| 8 | Llama 4 Maverick | 5.5 |
| 9 | O1 (2024-12-17) | 4.75 |
| 10 | Qwen 2.5 72B Instruct | 2.25 |
| 11 | Doubao-1.5-Pro | 2 |
Interactive version: theaggregate.ai/benchmark?slug=multi-swe-bench-mini-mopenhands · How It Works · Data refreshed daily, snapshot 2026-09-26.