Chat2Workflow - Pass Rate: leaderboard
Metric: Pass rate (%) on Chat2Workflow (79 instructions in 27 multi-turn tasks, pooled over six domains): share of generated workflows that pass the format, node-selection and structure checks (valid JSON converted to a Dify YAML workflow with every mandatory node), judged by GPT-5.1; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 80.17 |
| 2 | Claude Sonnet 4.5 | 71.31 |
| 3 | GLM-4.7 | 69.2 |
| 4 | GPT-5.2 | 67.51 |
| 5 | GLM-4.6 | 62.45 |
| 6 | Kimi K2 (Thinking) | 57.81 |
| 7 | DeepSeek V3.1 | 51.48 |
| 8 | GPT-5.1 | 47.26 |
| 9 | DeepSeek V3.2 | 43.46 |
| 10 | Qwen 3 Coder 480B A35B Instruct | 42.19 |
| 11 | Qwen 3 235B A22B | 40.93 |
| 12 | Qwen 3 32B | 36.71 |
| 13 | Kimi K2 | 36.29 |
| 14 | Qwen 3 14B | 27.43 |
| 15 | Qwen 3 8B | 13.92 |
Interactive version: theaggregate.ai/benchmark?slug=chat2workflow-pass-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.