BabyVisionBrowse 296

BabyVision

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

Version not specifiedExact reported variant
Vision6 ranked models6 reported values2 reportsHigher is better

Top rankings

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

6
RankModelBest scoreBest reported setting
1DeepSeek V4.1 FlashDeepSeek89.6%Reported configurationDeepSeek report1 value · 1 reportSep 10, 2026 · source
2GPT-5.5OpenAI83.6%xhigh effortMeta report1 value · 1 reportJul 9, 2026 · source
3Claude Opus 4.8Anthropic81.2%max effortMeta report1 value · 1 reportJul 9, 2026 · source
4Muse Spark 1.1Meta76.3%xhigh effortMeta report1 value · 1 reportJul 9, 2026 · source
5Gemini 3.1 ProGoogle51.5%high effortMeta report1 value · 1 reportJul 9, 2026 · source
6Muse Spark 1.0Meta39.9%Reported configurationMeta report1 value · 1 reportJul 9, 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 BabyVision (w/tools) retained. 388 questions; gpt-oss-120B high-reasoning judge; with code execution.

Method / source