SWE-Together — leaderboard
Interactive coding-agent evaluation over 109 real multi-turn software tasks (bugfix, feature, refactor) drawn from 27 open-source repositories across TypeScript, Go, Python and Rust. Agents work through multi-turn user intents in a harness (OpenCode, mini-swe-agent); each attempt is scored by a rubric jury on goal completion, averaged across tasks and replicates.
Metric: Jury Score (%). Source: togetherbench.com. Status: saturation imminent. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 80.06 |
| 2 | GPT-5.5 | 76.31 |
| 3 | Claude Opus 4.6 | 75.49 |
| 4 | GLM-5.2 | 73.53 |
| 5 | GLM-5.1 | 72.89 |
| 6 | DeepSeek V4 Pro | 67.93 |
| 7 | MiniMax-M2.7 | 62.99 |
Interactive version: theaggregate.ai/benchmark?slug=swe-together · How the rankings work · Data refreshed daily, snapshot 2026-07-22.