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

#ModelScoreOverall rank
1Gemini 3 Pro (Preview)69.63#123
2Claude Sonnet 4.562.22#267
3GPT-5.250.37#190
4Kimi K2 (Thinking)46.67
5GLM-4.745.18#383
6GPT-5.140.74#248
7GLM-4.639.26#496
8DeepSeek V3.236.29#425
9Qwen 3 235B A22B34.07#633
10DeepSeek V3.134.07#511
11Qwen 3 Coder 480B A35B Instruct28.89#655
12Kimi K227.4#448
13Qwen 3 14B14.08#1284
14Qwen 3 32B13.33#983
15Qwen 3 8B4.45#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.