Skip to content

Benchmark

Sayf AthenaBench TAA accuracy

Vision benchmarks measure how well models understand images. Higher scores are better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
1.04

Score distribution

0.232
Mean
0.22
Median
0.102
Std dev
0.16
10th percentile
0.42
90th percentile
0.11
Min
0.110.42
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.04 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: Sayf-eval. Copyright (c) 2026 Qatar Computing Research Institute (QCRI). MIT License. (licence)