PrepBench - GUI Workflow: leaderboard
End-to-end accuracy (%) of LLM agents that turn an ambiguous data-preparation request into an executable GUI operator workflow on PrepBench (2026), a benchmark of natural-language data-preparation requests over imperfect real tables. Agents may ask a simulated user clarification questions; higher is better.
Metric: End-to-end GUI workflow accuracy (%): from the original ambiguous request, the agent must produce an executable operator workflow whose output table matches the reference, PrepBench natural-language data-preparation tasks, LLM agent at temperature 0.7 with Clarify (budgeted, answered by a DeepSeek-V3.2 user simulator), Profile, Code and Translate actions; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 Codex | 34.6 | #295 |
| 2 | Kimi K2 (Thinking) | 30.1 | |
| 3 | Claude Sonnet 4.5 | 24.5 | #261 |
| 4 | Gemini 3 Flash | 22.2 | #175 |
| 5 | GLM-4.7 | 19.9 | #380 |
| 6 | Qwen 3 235B A22B | 19.3 | #628 |
| 7 | DeepSeek V3.2 | 15.7 | #419 |
| 8 | Grok Code Fast 1 | 13.1 | #703 |
| 9 | Devstral 2 | 8.5 | #1010 |
| 10 | GPT-4o | 5.2 | #751 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=prepbench-gui-workflow · How It Works · Data refreshed daily, snapshot 2026-11-21.