CelloAI-Doc-Bench - Tag Coverage F1: leaderboard
Metric: Tag-level F1 (0-1, times 100) of the @param and @return tags in Doxygen-style comments generated by the model for scientific/HPC C++ and CUDA functions (FastCaloSim and ATLAS Athena code), temperature 0.1, mean of 10 runs, against the function's real parameters and return values; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-OSS-120B | 95.2 | #330 |
| 2 | Phi-4 | 93.4 | #701 |
| 3 | Qwen 3 8B | 90.8 | #667 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=celloai-doc-bench-tag-coverage-f1 · How It Works · Data refreshed daily, snapshot 2026-10-11.