OpenSkillEval: leaderboard
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill ecosystem rapidly expands, it remains unclear how different models and agent frameworks interact with skills, how to evaluate skill quality, and how users should
Metric: Overall avg. (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 4.51 | #63 |
| 2 | GPT-5.5 | 4.47 | #31 |
| 3 | Claude Sonnet 4.6 | 4.43 | #90 |
| 4 | GLM-5.1 | 4.42 | #97 |
| 5 | Kimi K2.6 | 4.2 | #104 |
| 6 | GPT-5.2 | 4.03 | #110 |
| 7 | MiniMax-M2.7 | 4.02 | #258 |
| 8 | Gemini 3.1 Pro (Preview) | 4 | #58 |
| 9 | GPT-5.3 Codex | 3.76 | #69 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openskilleval · How It Works · Data refreshed daily, snapshot 2026-10-20.