Skip to content

Benchmark

MM-Mind2Web

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

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

60.1%
Mean
60.7%
Median
3.3%
Std dev
55.8%
10th percentile
63.7%
90th percentile
55.8%
Min
55.8%63.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Nova Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.7%
2Nova Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.7%
3Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.8%

Data credits: Data by LLM Stats