List your company

Document Visual Question Answering on InfoQA 105 (test)

86.9ScoreGemini 3 Pro
52.5861.4970.479.31Jan 15, 2026

Evaluation results

MethodLinks
Gemini 3 ProModel Category=API call only2026.0186.9
Qwen3-VL-8BModel Category=Open weights only2026.0183.1
GPT-5Model Category=API call only2026.0183
GPT-5 miniModel Category=API call only2026.0182.2
Gemini 2.5 ProModel Category=API call only2026.0182
Molmo-72BModel Category=Molmo1 family2026.0181.9
Gemini 2.5 FlashModel Category=API call only2026.0180.9
Eagle2.5-8BModel Category=Open weights only2026.0180.4
Qwen3-VL-4BModel Category=Open weights only2026.0180.3
GLM-4.1V-9BModel Category=Open weights only2026.0180.3
Molmo2-8BModel Category=Molmo2 family2026.0180.1
PLM-8BModel Category=Open models2026.0180
InternVL3.5-8BModel Category=Open weights only2026.0179.1
Molmo2-4BModel Category=Molmo2 family2026.0178.6
InternVL3.5-4BModel Category=Open weights only2026.0178
Molmo2-O-7BModel Category=Molmo2 family2026.0177.9
Keye-VL-1.5-8BModel Category=Open weights only2026.0174.9
PLM-3BModel Category=Open models2026.0174.6
MiniCPM-V-4.5-8BModel Category=Open weights only2026.0173.4
Molmo-7B-DModel Category=Molmo1 family2026.0172.6
Molmo-7B-OModel Category=Molmo1 family2026.0170
Claude Sonnet 4.5Model Category=API call only2026.0165.9
MolmoE-1BModel Category=Molmo1 family2026.0153.9