Skip to content

Benchmark

ClawBench

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

Models measured
7
Scores recorded
7
Sources
1
IQ weight
0.14

Score distribution

15%
Mean
18.3%
Median
11.1%
Std dev
3.3%
10th percentile
24.2%
90th percentile
0.7%
Min
0.7%33.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.14 for chat models, measured over 7 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: Steel.dev Agent Leaderboards, MIT (licence)