An open benchmark for goal-oriented software engineering. Models maintain and improve codebases through multi-round tournaments, with win rate and Elo measuring strategic planning, log analysis, code evolution, and long-term maintenance.
Browse the latest scores, model modes, release dates, and parameter sizes for CodeClash.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Claude Sonnet 4.5 Standard ModeTools | 1389.00 | 2025-09-30 | Unknown | Closed | |
 GPT-5 Standard ModeTools | 1360.00 | 2025-08-07 | Unknown | Closed | |
OpenAI o3 Standard ModeTools | 1343.00 | 2025-04-16 | Unknown | Closed | |
4 | Claude Sonnet 4 Standard ModeTools | 1223.00 | 2025-05-23 | Unknown | Closed |
5 | GPT-5-mini Standard ModeTools | 1200.00 | 2025-08-07 | Unknown | Closed |
6 |  Gemini 2.5-Pro Standard ModeTools | 1125.00 | 2025-06-05 | Unknown | Closed |
7 |  Grok Code Fast 1 Standard ModeTools | 1004.00 | 2025-08-28 | Unknown | Closed |
8 |  Qwen3-Coder-480B-A35B Standard ModeTools | 952.00 | 2025-07-23 | 480B | Free Commercial |
