XRepoTest - Julia - Test Pass Rate: leaderboard
XRepoTest (arXiv 2608.25939v1, Appendix Table A.4): repository-level unit-test generation in real open-source Julia projects, standard single-turn setting with greedy decoding, with generated tests executed in containers. Share of all focal functions whose generated test suite executes and passes, percent. Higher is better.
Metric: Passing generated test suites (%; of all focal functions). Source: arxiv.org. Saturation forecast: Around 2029. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 19.88 | #148 |
| 2 | GPT-5.2 | 16.52 | #115 |
| 3 | Claude Haiku 4.5 (20251001) | 12.57 | #264 |
| 4 | DeepSeek V4 Pro | 11.4 | #112 |
| 5 | GLM-5 | 5.41 | #149 |
| 6 | Qwen3 Coder Next | 5.12 | #331 |
| 7 | Yi-Coder-9B-Chat | 4.82 | #1244 |
| 8 | GPT-OSS-120B | 4.39 | #346 |
| 9 | MiniMax-M2.7 | 4.39 | #270 |
| 10 | DeepSeek V3.2 | 3.95 | #210 |
| 11 | Llama 3.3 70B Instruct | 3.07 | #541 |
| 12 | Kimi K2.5 | 2.63 | #152 |
| 13 | Codestral-22B-v0.1 | 2.05 | #850 |
| 14 | Qwen 3 8B | 0.88 | #678 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=xrepotest-julia-test-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.