CommitSuite - Commit Classification: leaderboard
Metric: Accuracy (%, times 100) of ten-way Conventional Commits type classification (feat, fix, perf, style, refactor, docs, test, ci, build, chore) on the balanced 1,160-commit Ten-category-eval set of CommitSuite (116 human-checked commits per type), zero-shot prompting with the commit diff and context; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 63.8 |
| 2 | Gemini 2.0 Flash | 62.9 |
| 3 | Claude 3.7 Sonnet | 60.9 |
| 4 | GPT-4.1 | 60.8 |
| 5 | DeepSeek V3 | 59.7 |
| 6 | GPT-4o Mini | 55.9 |
Interactive version: theaggregate.ai/benchmark?slug=commitsuite-commit-classification · How It Works · Data refreshed daily, snapshot 2026-10-07.