List your company

Visual Question Answering on HR-Bench 8k

14.4C@1SIEVES
-0.5763.3127.211.088Apr 28, 2026

Evaluation results

MethodLinks
SIEVESReasoner=Gemini-3-Pro, Localization setting=w/ localization2026.0414.480.84.490.1
SIEVESReasoner=o3, Localization setting=w/ localization2026.04867.79.382
SelectorReasoner=Gemini-3-Pro, Localization setting=w/o localization2026.045.874.55.485.6
SelectorReasoner=Gemini-3-Pro, Localization setting=w/ localization2026.044.580.13.590.1
SIEVESReasoner=Pixel-Reasoner, Localization setting=w/ localization2026.042.341.118.168.4
Zero-shot logitReasoner=Gemini-3-Pro, Localization setting=w/ localization2026.041.479.94.990.1
SelectorReasoner=o3, Localization setting=w/ localization2026.04161.710.582
SelectorReasoner=Pixel-Reasoner, Localization setting=w/o localization2026.040.930.820.365.6
LogprobsReasoner=Pixel-Reasoner, Localization setting=w/ localization2026.040.328.922.668.4
SelectorReasoner=o3, Localization setting=w/o localization2026.040.333.319.272.1
LogprobsReasoner=Pixel-Reasoner, Localization setting=w/o localization2026.0406.230.365.6
Zero-shot verb.Reasoner=Pixel-Reasoner, Localization setting=w/ localization2026.04013.328.968.4
Zero-shot logitReasoner=Pixel-Reasoner, Localization setting=w/ localization2026.04032.821.368.4
SelectorReasoner=Pixel-Reasoner, Localization setting=w/ localization2026.04042.717.468.4
Zero-shot verb.Reasoner=o3, Localization setting=w/ localization2026.04054.213.582
Zero-shot logitReasoner=o3, Localization setting=w/ localization2026.04056.313.182
Zero-shot verb.Reasoner=Gemini-3-Pro, Localization setting=w/ localization2026.04071.46.490.1