SWE-Misbehavior - Code Generation Agno - Context: leaderboard
SWE-Misbehavior:fixed Agno coding agent on Code Generation tasks; rate of boundary violations, lower is better. Rule-based code/file metrics and LLM-judged instruction/environment/resource metrics; the paper Qwen-Coder-30B label lacks an exact generation binding and remains source-qualified. Misbehavior Rate (%).
Metric: Misbehavior Rate (%). Source: arxiv.org. Saturation forecast: Around 2029. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 15.5 | #104 |
| 2 | Gemini 2.5 Flash | 13.17 | #242 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=swe-misbehavior-code-generation-agno-context · How It Works · Data refreshed daily, snapshot 2026-10-23.