ZeroBench-mainBrowse 296

ZeroBench-main

Can the model extract and reason over information in images or documents?

Version not specifiedExact reported variant
Vision1 ranked models1 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

1
RankModelBest scoreBest reported setting
1DeepSeek V4.1 FlashDeepSeek49.0%Reported configurationDeepSeek report1 value · 1 reportSep 10, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology

Can the model extract and reason over information in images or documents?

Visual perception and multimodal reasoning under the reported protocol. Higher is better. The value is the percentage reported in this lab's table.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

DeepSeek's official V4.1-Flash release table; exact source label ZeroBench-main (w/tools) retained.

Method / source