Benchmark
Online-Mind2Web Medium (auto)
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.
All agentic benchmarksScores from Online-Mind2Web Leaderboard data.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 40.1%
- Mean
- 36.1%
- Median
- 11.8%
- Std dev
- 28.1%
- 10th percentile
- 56.2%
- 90th percentile
- 28.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 3.7· Online-Mind2Web Leaderboard data | 56.2% |
| 2 | GPT 4o· Online-Mind2Web Leaderboard data | 36.1% |
| 3 | Claude 3.5 Sonnet· Online-Mind2Web Leaderboard data | 28.1% |
Data credits: Online-Mind2Web Leaderboard (OSU NLP), Apache-2.0 (licence)