Software Engineering Arena - Agent Arena — leaderboard
Metric: Elo Rating. Source: huggingface.co. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini CLI | 1018.07 |
| 2 | Qwen Code | 1016 |
| 3 | Cursor | 1015.26 |
| 4 | OpenAI Codex | 1009.15 |
| 5 | Claude Code | 1004.49 |
| 6 | MiniMax CLI | 998.82 |
| 7 | Grok CLI | 969.47 |
| 8 | Kimi Code | 968.74 |
Interactive version: theaggregate.ai/benchmark?slug=software-engineering-arena-agent-arena · How the rankings work · Data refreshed daily, snapshot 2026-07-22.