Agent-Diff - Pass Rate: leaderboard
Metric: Pass rate (%) on Agent-Diff's 224 enterprise API tasks (Box, Google Calendar, Linear, Slack replicas) in the no-documentation setting, code-executing agent, three trials per task, graded by state-diff assertions with any unexpected side effect zeroing the task; a task passes when it is clean and every assertion holds; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.2 | 76 | #198 |
| 2 | Devstral 2 | 74 | #394 |
| 3 | Gemini 3 Flash (Preview) | 67 | #78 |
| 4 | Kimi K2 0905 | 64 | #282 |
| 5 | GPT-OSS-120B | 60 | #330 |
| 6 | Grok 4.1 Fast | 52 | #208 |
| 7 | Claude Haiku 4.5 | 50 | #271 |
| 8 | Llama 4 Scout | 29 | #646 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=agent-diff-pass-rate · How It Works · Data refreshed daily, snapshot 2026-10-11.