Skip to content

Benchmark

Vals Terminal-Bench-Science

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

Models measured
46
Scores recorded
46
Sources
1
IQ weight
4.18

Score distribution

17.5%
Mean
7.1%
Median
20.1%
Std dev
1.4%
10th percentile
52.9%
90th percentile
0%
Min
0%71.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 4.18 for chat models, measured over 46 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard