Software Engineering Arena - Model Arena — leaderboard

Metric: Elo Rating. Source: huggingface.co. 23 models tracked.

Top models

#ModelScore
1Llama 3.1 70B Instruct1002
2DeepSeek V3.1 Terminus1002
3Grok Code Fast 11002
4MiMo-V2-Flash1002
5O3 Mini (High)1002
6Gemini 2.5 Pro998
7GPT-4.1998
8Qwen 3 8B998
9Claude Haiku 4.5998
10Gemini 2.5 Flash Lite998
11NVIDIA Nemotron Nano 9B V2998
12GLM-4.5998
13Mixtral 8x22B Instruct998
14GPT-5 Pro998
15Ministral 8B998

Interactive version: theaggregate.ai/benchmark?slug=software-engineering-arena-model-arena · How the rankings work · Data refreshed daily, snapshot 2026-07-22.