Skip to content

Benchmark

Online-Mind2Web

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

Models measured
5
Scores recorded
6
Sources
2
IQ weight
0.61

Score distribution

61.8%
Mean
69%
Median
26%
Std dev
30.7%
10th percentile
92.8%
90th percentile
29%
Min
29%92.8%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.61 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
1GPT 5.4screenshot observations only· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.8%
2GPT 5.4· Online-Mind2Web Leaderboard data92.7%
3Gemini 2.5 Computer Use· Online-Mind2Web Leaderboard data69%
4Claude Sonnet 3.7· Online-Mind2Web Leaderboard data56.3%
5GPT 4o· Online-Mind2Web Leaderboard data30.7%
6Claude 3.5 Sonnet· Online-Mind2Web Leaderboard data29%

Data credits: Online-Mind2Web Leaderboard (OSU NLP), Apache-2.0 (licence) · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.