SWE-bench Live C# (28 tasks, SWE-agent): leaderboard
SWE-bench-Live's C# split (Microsoft, 2026 multi-language update): recent GitHub issues from C# repositories, built into runnable environments by the RepoLaunch pipeline and graded by the repository's tests. This board is the 28-task snapshot under the SWE-agent harness, 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 2029. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 21.43 | #142 |
| 2 | GPT-5.2 (Medium) | 21.43 | #110 (GPT-5.2) |
| 3 | DeepSeek V3.1 Terminus | 21.43 | #220 |
| 4 | Gemini 3 Flash | 14.29 | #99 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-live-c-sharp-28-tasks-swe-agent · How It Works · Data refreshed daily, snapshot 2026-10-20.