Chat2Workflow - Document: 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. Resolve rate in percent on the document processing tasks; higher is better.
Metric: Resolve rate (%) on Chat2Workflow document processing tasks: share of test cases where the workflow the model generates for the current round of a multi-turn request, deployed on Dify 1.9.2, executes and its output satisfies every requirement of the instruction, 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) | 69.63 | #123 |
| 2 | Claude Sonnet 4.5 | 62.22 | #267 |
| 3 | GPT-5.2 | 50.37 | #190 |
| 4 | Kimi K2 (Thinking) | 46.67 | |
| 5 | GLM-4.7 | 45.18 | #383 |
| 6 | GPT-5.1 | 40.74 | #248 |
| 7 | GLM-4.6 | 39.26 | #496 |
| 8 | DeepSeek V3.2 | 36.29 | #425 |
| 9 | Qwen 3 235B A22B | 34.07 | #633 |
| 10 | DeepSeek V3.1 | 34.07 | #511 |
| 11 | Qwen 3 Coder 480B A35B Instruct | 28.89 | #655 |
| 12 | Kimi K2 | 27.4 | #448 |
| 13 | Qwen 3 14B | 14.08 | #1284 |
| 14 | Qwen 3 32B | 13.33 | #983 |
| 15 | Qwen 3 8B | 4.45 | #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-document · How It Works · Data refreshed daily, snapshot 2026-11-22.