Multi-SWE-bench Go (MopenHands): leaderboard
Metric: Resolved rate (%). Source: multi-swe-bench.github.io. Saturation forecast: Around 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 12.62 |
| 2 | Claude 3.7 Sonnet (20250219) | 7.48 |
| 3 | Claude 3.5 Sonnet (20241022) | 6.78 |
| 4 | Llama 4 Maverick | 5.61 |
| 5 | O1 (2024-12-17) | 3.74 |
| 6 | GPT-4o (2024-11-20) | 3.5 |
| 7 | O3 Mini (2025-01-31) (High) | 2.34 |
| 8 | Doubao-1.5-Pro | 1.64 |
| 9 | Qwen 2.5 72B Instruct | 1.4 |
| 10 | DeepSeek V3 | 0.7 |
| 11 | DeepSeek R1 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=multi-swe-bench-go-mopenhands · How It Works · Data refreshed daily, snapshot 2026-09-26.