Software Engineering Arena - Model Arena: leaderboard
Software Engineering Arena model-only preference leaderboard for software-engineering task performance.
Metric: Elo Rating. Source: huggingface.co. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B Instruct | 1002 | #561 |
| 2 | O3 Mini (High) | 1002 | #272 (O3 Mini) |
| 3 | MiMo-V2-Flash | 1002 | #372 |
| 4 | DeepSeek V3.1 Terminus | 1002 | #220 |
| 5 | Grok Code Fast 1 | 1002 | #337 |
| 6 | Qwen Turbo | 1002 | #699 |
| 7 | Qwen Plus | 1002 | #385 |
| 8 | Gemini 2.5 Pro | 998 | #152 |
| 9 | GPT-4.1 | 998 | #248 |
| 10 | Claude Haiku 4.5 | 998 | #280 |
| 11 | Qwen 3 8B | 998 | #674 |
| 12 | Gemini 2.5 Flash Lite | 998 | #422 |
| 13 | Mixtral 8x22B Instruct | 998 | #728 |
| 14 | GLM-4.5 | 998 | #275 |
| 15 | NVIDIA Nemotron Nano 9B V2 | 998 | #823 |
Interactive version: theaggregate.ai/benchmark?slug=software-engineering-arena-model-arena · How It Works · Data refreshed daily, snapshot 2026-10-20.