Skip to content

Benchmark

Vals Finance Agent v2.1

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

Models measured
42
Scores recorded
42
Sources
1
IQ weight
1.92

Score distribution

61.2%
Mean
61.6%
Median
5.6%
Std dev
54.3%
10th percentile
67.5%
90th percentile
44.8%
Min
44.8%69.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.92 for chat models, measured over 42 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard