List your company

Visual Question Answering on IRIS 1.0 (ambiguous trials)

59.3Accuracy (Image Only)Gemini 2.5 Pro
49.31651.90854.557.092Feb 18, 2026

Evaluation results

MethodLinks
Gemini 2.5 ProTemporal Window=±1s around speech onset2026.0259.382.323—
Qwen 2.5 VL 32BTemporal Window=±1s around speech onset2026.0256.27316.7—
Claude 4.1 OpusTemporal Window=±1s around speech onset2026.0255.27216.7—
Gemini 2.5 FlashTemporal Window=±1s around speech onset2026.0254.283.329—
Claude Sonnet 4Temporal Window=±1s around speech onset2026.0254.27419.8—
GPT-5Temporal Window=±1s around speech onset2026.0253.776.522.8—
Ovis 2.5 9BTemporal Window=±1s around speech onset2026.0252.569.517—
Qwen 2.5 VL 3BTemporal Window=±1s around speech onset2026.025254.52.50.48
Qwen 2.5 VL 7BTemporal Window=±1s around speech onset2026.0251.763.712—
GPT-5 MiniTemporal Window=±1s around speech onset2026.0249.78333.2—