llava-onevision-qwen2-72B-ov-chat-hf: benchmark results

Provider: LLaVA Team.

Aggregate Rating 1479 ± 41, rank #2654 of 10552 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
CoreCognition Image + Video Intentionality81.93Accuracy (%)94.1
CoreCognition Image + Video Mechanicalreasoning64.61Accuracy (%)76.1
CoreCognition Image + Video Hierarchy63.67Accuracy (%)74.8
CoreCognition Image + Video Boundary79.4Accuracy (%)71.4
CoreCognition Image + Video Conservation52.85Accuracy (%)64.3
CoreCognition Image + Video Perceptualconstancy66.67Accuracy (%)56.3
CoreCognition Image + Video Spatiality41.75Accuracy (%)54.2
CoreCognition Image + Video Mean54.19Accuracy (%)52.1
CoreCognition Image + Video Toolusing54.96Accuracy (%)51.3
CoreCognition Image + Video Continuity57.27Accuracy (%)48.7
TurtleAI - Hand-Drawn6.86Success rate (%) on the 102 TurtleAI-DSCraft tasks (hand-dra47.1
TurtleAI - Real4.9Success rate (%) on the 102 TurtleAI-DSReal tasks (XLogoOnli35.3

Interactive version: theaggregate.ai/model?slug=llava-onevision-qwen2-72b-ov-chat-hf · How It Works · Data refreshed daily, snapshot 2026-11-16.