Vision & multimodal understanding

A model's score is built only from results that someone other than its maker ran.

• The scoring set is the benchmarks chosen for this specialty. A benchmark takes part only when at least 5 models have an independent or third-party result on it.
• Each result is rescaled to 0 to 1, and a model's best setting counts.
• The score is the average over the benchmarks a model has, times 100.
• A model ranks only when it has results on enough of them. The rest show "Not enough independent results yet".
• Self-reported results are shown but never counted.

Method: category-2026-09-29.1

Scoring set: MMMU-Pro, ZeroBench, GeoBench, Visual Physics Comprehension Test (VPCT), Furniture Assembly.

Effective set (used for the score today): GeoBench, Visual Physics Comprehension Test (VPCT), Furniture Assembly

• MMMU-Pro: no importable independent results yet
• ZeroBench: no importable independent results yet

• CharXiv (Reasoning)ActiveSaturated0 results
• Furniture AssemblyActiveHeadroomCounts toward the score27 results
• GeoBenchActiveNear-ceilingCounts toward the score32 results
• MMMUSupersededNear-ceiling0 results
• MMMU-ProActiveNear-ceilingCounts toward the score0 results
• Video-MMMUActiveNear-ceiling0 results
• Visual Physics Comprehension Test (VPCT)ActiveNear-ceilingCounts toward the score38 results
• ZeroBenchActiveHeadroomCounts toward the score0 results