HyperAI

Multimodal Reasoning On Rebus

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Comparison Table
Model NameAccuracy
rebus-a-robust-evaluation-benchmark-of-10.6
rebus-a-robust-evaluation-benchmark-of-10.9
rebus-a-robust-evaluation-benchmark-of-10.9
rebus-a-robust-evaluation-benchmark-of-11.8
rebus-a-robust-evaluation-benchmark-of-113.2
rebus-a-robust-evaluation-benchmark-of-11.5
rebus-a-robust-evaluation-benchmark-of-10.9
rebus-a-robust-evaluation-benchmark-of-124.0