CodeARC - Annotated: leaderboard

Metric: Success Rate (%; descriptive function names, 1,114 functions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 18 models tracked.

Top models

#ModelScore
1O3 Mini59.5
2O1 Mini53.2
3DeepSeek R149.8
4Claude 3.7 Sonnet39
5Llama 3.1 405B Instruct38.6
6GPT-4o37.8
7DeepSeek V337.7
8Llama 3.1 70B Instruct30.1
9Qwen 2.5 72B Instruct30.1
10Qwen 2.5 7B Instruct29.2
11Llama 3.2 90B Vision Instruct28.4
12GPT-4o Mini26.1
13Mixtral 8x22B Instruct (v0.1)25.1
14Llama 3.2 11B Instruct24.9
15Mixtral 8x7B Instruct (v0.1)20.3

Interactive version: theaggregate.ai/benchmark?slug=codearc-annotated · How It Works · Data refreshed daily, snapshot 2026-09-24.