Skip to content

Benchmark

Vals Terminal-Bench 2.1

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

Models measured
69
Scores recorded
69
Sources
1
IQ weight
2.14

Score distribution

61.8%
Mean
67%
Median
17%
Std dev
41.6%
10th percentile
81.3%
90th percentile
10.9%
Min
10.9%87.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.14 for chat models, measured over 69 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 51–69 of 69 results.