Skip to content

Benchmark

BrowserGym WorkArena-L3

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

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.95

Score distribution

2%
Mean
0%
Median
4.3%
Std dev
0%
10th percentile
11.5%
90th percentile
0%
Min
0%11.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.95 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: BrowserGym Leaderboard (ServiceNow), MIT (licence)