benchmark evidence
MMStar
MMStar: manually filtered multimodal benchmark requiring genuine visual perception, resistant to contamination.
activeupstream source ->
no matched results
No public rows from this source currently map to an active callable model.
what this result means
MMStar: manually filtered multimodal benchmark requiring genuine visual perception, resistant to contamination.
This benchmark contributes direct public evidence. Read its scope before generalizing the result.
A win here is a win on MMStar. Broad task pages require independent corroboration before naming a general winner.
source record
category: multimodal
metric: accuracy
matched models: 0
latest source date: date unavailable
direction: higher is better