GitTaskBench (SWE-Agent) - Execution Completion: leaderboard
Metric: Execution completion rate (%). Source: gittaskbench.github.io. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) | 64.81 |
| 2 | Claude 3.5 Sonnet (20241022) | 41.67 |
| 3 | GPT-4.1 | 38.89 |
| 4 | O3 Mini (Medium) | 25.93 |
| 5 | Llama 3.3 70B Instruct | 25.83 |
| 6 | DeepSeek V3 (0324) | 18.52 |
| 7 | GPT-4o (2024-08-06) | 17.58 |
| 8 | Qwen 3 32B (Thinking) | 16.67 |
| 9 | Qwen 3 32B (Non-reasoning) | 7.41 |
Interactive version: theaggregate.ai/benchmark?slug=gittaskbench-swe-agent-execution-completion · How It Works · Data refreshed daily, snapshot 2026-09-26.