SWE-bench Live Go (138 tasks, AMI Agent): leaderboard
SWE-bench-Live's Go split (Microsoft, 2026 multi-language update): recent GitHub issues from Go repositories, built into runnable environments by the RepoLaunch pipeline and graded by the repository's tests. This board is the 138-task snapshot under AMI Agent, a submitted agent, scored as the percentage of tasks resolved; higher is better. The split grows, so each snapshot size is its own board.
Metric: Resolved rate (%). Source: swe-bench-live.github.io. Saturation forecast: Around May 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 74.64 | #100 |
| 2 | Claude Sonnet 4.6 | 71.74 | #158 |
| 3 | Claude Haiku 4.5 | 65.22 | #568 |
| 4 | Gemini 3.6 Flash | 56.52 | #72 |
| 5 | Gemini 3.1 Pro (Preview) | 52.17 | #91 |
| 6 | Qwen 3.8 27B | 29.71 | #199 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-live-go-138-tasks-ami-agent · How It Works · Data refreshed daily, snapshot 2026-11-12.