Skip to content

Benchmark

BrowserGym WebLINX

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.43

Score distribution

10.9%
Mean
11.6%
Median
2.2%
Std dev
7.9%
10th percentile
13.7%
90th percentile
7.9%
Min
7.9%13.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.43 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude 3.5 SonnetGenericAgent· BrowserGym Leaderboard13.7%
2GPT 4oGenericAgent· BrowserGym Leaderboard12.5%
3GPT-4o miniGenericAgent· BrowserGym Leaderboard11.6%
4Llama 3.1 70BGenericAgent· BrowserGym Leaderboard8.9%
5Llama 3.1 405BGenericAgent· BrowserGym Leaderboard7.9%

Data credits: BrowserGym Leaderboard (ServiceNow), MIT (licence)