Blueprint-Bench
Can the model extract and reason over information in images or documents?
Vision8 ranked models9 reported values2 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | GPT-5.5OpenAI | 36.2% | Reported configurationAnthropic report2 values · 2 reportsJun 9, 2026 · source |
| 2 | Gemini 3.5 FlashGoogle | 33.6% | Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source |
| 3 | Gemini 3.1 Pro PreviewGoogle | 26.5% | Reported configurationAnthropic report1 value · 1 reportJun 9, 2026 · source |
| 4 | Gemini 3.1 ProGoogle | 26.5% | Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source |
| 5 | Claude Opus 4.7Anthropic | 24.5% | Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source |
| 6 | Claude Opus 4.8Anthropic | 14.5% | Reported configurationAnthropic report1 value · 1 reportJun 9, 2026 · source |
| 7 | Claude Sonnet 4.6Anthropic | 6.7% | Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source |
| 8 | Gemini 3 FlashGoogle | 0.0% | Reported configurationGoogle report1 value · 1 reportMay 19, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
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.
Normalized score.
Method / source