Chat2Workflow - Pass Rate: leaderboard
Chat2Workflow (2026) tests whether language models build executable Dify workflows from multi-turn natural-language requests drawn from real business workflows, run against test cases. Pass rate in percent, the share of generated workflows that pass format, node and structure checks; higher is better.
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 February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 80.17 | #123 |
| 2 | Claude Sonnet 4.5 | 71.31 | #267 |
| 3 | GLM-4.7 | 69.2 | #383 |
| 4 | GPT-5.2 | 67.51 | #190 |
| 5 | GLM-4.6 | 62.45 | #496 |
| 6 | Kimi K2 (Thinking) | 57.81 | |
| 7 | DeepSeek V3.1 | 51.48 | #511 |
| 8 | GPT-5.1 | 47.26 | #248 |
| 9 | DeepSeek V3.2 | 43.46 | #425 |
| 10 | Qwen 3 Coder 480B A35B Instruct | 42.19 | #655 |
| 11 | Qwen 3 235B A22B | 40.93 | #633 |
| 12 | Qwen 3 32B | 36.71 | #983 |
| 13 | Kimi K2 | 36.29 | #448 |
| 14 | Qwen 3 14B | 27.43 | #1284 |
| 15 | Qwen 3 8B | 13.92 | #1890 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=chat2workflow-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-22.