Skip to content

Benchmark

Design Arena Elo (agents/agentic_gamedev)

Agentic benchmarks measure how well models carry out tasks that take several steps. Higher scores are better.

Models measured
25
Scores recorded
26
Sources
1
IQ weight
2.32

Score distribution

1,142.5
Mean
1,127
Median
84.4
Std dev
1,061
10th percentile
1,231
90th percentile
954
Min
9541,408
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.32 for chat models, measured over 25 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard