LibEvoBench - Stable APIs: leaderboard
Metric: Average task performance (0-100) on stable APIs (identical signature in every covered version): mean of four task metrics (API calling with version constraint, exact match; API calling parameter recall given name and version; API identification from a redacted docstring, exact match; signature recall F1) averaged over PyTorch, NumPy and SciPy versions, temperature 0 where supported and no thinking budget; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 92.3 |
| 2 | GPT-5.4 | 92 |
| 3 | Claude Sonnet 4.6 | 89.3 |
| 4 | Claude Sonnet 4 | 87.8 |
| 5 | Gemini 3 Flash (Minimal) | 87.8 |
| 6 | GPT-4.1 | 84.3 |
| 7 | GPT-5.1 | 83.8 |
| 8 | GPT-5 | 83 |
| 9 | Gemini 2.5 Flash (Non-reasoning) | 81.6 |
| 10 | Qwen 3.5 397B A17B (Non-reasoning) | 80.2 |
| 11 | Gemini 2.0 Flash | 79.7 |
| 12 | Qwen 3.5 122B A10B (Non-reasoning) | 70.5 |
| 13 | Qwen 3.5 35B A3B (Non-reasoning) | 63.3 |
Interactive version: theaggregate.ai/benchmark?slug=libevobench-stable-apis · How It Works · Data refreshed daily, snapshot 2026-09-29.