Skip to content

Benchmark

OpenHands Index

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

Models measured
31
Scores recorded
31
Sources
1
IQ weight
1.83

Score distribution

52.6%
Mean
52.9%
Median
12%
Std dev
38.1%
10th percentile
66.7%
90th percentile
30.9%
Min
30.9%81%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.83 for chat models, measured over 31 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: OpenHands Index (All Hands AI), Apache-2.0 (licence)