CharXiv Reasoning (no tools)Browse 296

CharXiv Reasoning (no tools)

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

Version not specifiedExact reported variant
Vision15 ranked models22 reported values4 reportsHigher is better

Top rankings

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

15
RankModelBest scoreBest reported setting
1Gemini 3.8 FlashGoogle86.2%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
2GPT-5.6 TerraOpenAI85.9%Reported configurationGoogle DeepMind report2 values · 2 reportsSep 2, 2026 · source
3GPT-5.6 SolOpenAI85.8%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
4Gemini 3.6 FlashGoogle85.2%Reported configurationGoogle report2 values · 2 reportsAug 13, 2026 · source
5Gemini 3.7 FlashGoogle84.5%Reported configurationGoogle DeepMind report2 values · 2 reportsSep 2, 2026 · source
6Gemini 3.5 FlashGoogle84.2%Reported configurationGoogle report2 values · 2 reportsJul 21, 2026 · source
7GPT-5.5OpenAI84.1%Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source
8Claude Opus 5Anthropic83.7%Reported configurationGoogle DeepMind report1 value · 1 reportSep 2, 2026 · source
9Gemini 3.1 ProGoogle83.3%Reported configurationGoogle report2 values · 2 reportsJul 21, 2026 · source
10GPT-5.6 LunaOpenAI82.7%Reported configurationGoogle report1 value · 1 reportJul 21, 2026 · source
11Claude Opus 4.7Anthropic82.1%Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source
12Grok 4.5SpaceXAI81.6%Reported configurationGoogle report1 value · 1 reportJul 21, 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.

No tools. No tools. Gemini and GPT-5.6 Terra cells are Google-computed. Information synthesis from complex charts; no tools.

Method / source