Skip to content

Benchmark

xbench-$OneMillion-Bench

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
1.07

Score distribution

26.7%
Mean
26%
Median
8.3%
Std dev
15.8%
10th percentile
35.3%
90th percentile
13%
Min
13%42.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.07 for chat models, measured over 13 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard