Coding benchmark
SWE-bench Verified* leaderboard
SWE-bench Verified (mini-swe-agent-v2). Every model the catalog carries a published SWE-bench Verified* value for, ranked by that value.
A display-only SWE-bench Verified reference from Arcee AI's Trinity-Large-Thinking comparison chart.
SWE-bench Verified* ranking
5 models with a published SWE-bench Verified* value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Agent scaffold benchmark |
|---|---|---|---|
| 1 |  Claude Opus 4.6 | Anthropic | 75.6 |
| 2 |  MiniMax M2.7 | MiniMax | 75.4 |
| 3 |  GLM-5 | Z.AI | 72.8 |
| 4 |  Kimi K2.5 | Moonshot AI | 70.8 |
| 5 |  Trinity-Large-Thinking | Arcee AI | 63.2 |
Evidence key: Observed
Rows are ordered by the value Trinity-Large-Thinking: Scaling an Open Source Frontier Agent published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.