TestExplora-Lite (Black Box) - Entry Coverage: leaderboard
Metric: Entry coverage (%): line coverage of the functions under test achieved by the generated tests; TestExplora-Lite (517 samples from 330 pull requests with high-quality human docstrings); Black Box setting, where the model sees only the documentation and signatures of the functions under test; single model call with DocAgent-written documentation as the oracle; mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini | 59.72 | #176 |
| 2 | O4 Mini | 59.44 | #172 |
| 3 | O3 Mini | 56.43 | #266 |
| 4 | GPT-4o | 54.69 | #333 |
| 5 | Gemini 2.5 Pro | 53.24 | #145 |
| 6 | Qwen 3 Coder 30B A3B Instruct | 49.98 | #399 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=testexplora-lite-black-box-entry-coverage · How It Works · Data refreshed daily, snapshot 2026-10-11.