List your company

Multiple-Choice Question Answering on Image Implication Multiple-Choice 1.0 (test)

78AccuracyGemini-2.5-flash-thinking
13.5230.264763.74Feb 11, 2026

Evaluation results

MethodLinks
Gemini-2.5-flash-thinking2026.0278
MetaphorStar-32BParameters=32B2026.0278
Gemini-2.5-flash2026.0276
Gemini-3.0-pro2026.0276
GPT-4o2026.0274
GPT-4.12026.0274
Grok-3-reasoning2026.0274
MetaphorStar-7BParameters=7B2026.0274
QwenVL-2.5-72BParameters=72B2026.0272
InternVL3-78BParameters=78B2026.0270
Claude-3.5-Sonnet2026.0268
Grok-32026.0266
Doubao-1.5-thinking-vision-pro2026.0266
GLM-4V-plus2026.0264
MetaphorStar-3BParameters=3B2026.0264
QwenVL-2.5-32BParameters=32B2026.0262
QVQ-72BParameters=72B2026.0262
GLM-4.1V-8BParameters=8B2026.0260
Claude-4.0-Sonnet2026.0260
o4-mini2026.0258
QwenVL-2.5-3BParameters=3B2026.0248
QwenVL-2.5-7BParameters=7B2026.0246
DeepSeek-VL22026.0246
GPT-4o-mini2026.0244
LLaVA-1.5-7BParameters=7B2026.0216