Skip to content

Benchmark

Orak StreetFighterIII Elo

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

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

1,523.3
Mean
1,602.9
Median
79.9
Std dev
1,434.3
10th percentile
1,602.9
90th percentile
1,434.3
Min
1,434.31,602.9
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT 4ozero-shot· Orak leaderboard docs1,602.9
2o3 Minizero-shot· Orak leaderboard docs1,602.9
3GPT-4o minizero-shot· Orak leaderboard docs1,453
4Claude Sonnet 3.7zero-shot· Orak leaderboard docs1,434.3

Data credits: Orak leaderboard, KRAFTON AI (Park et al., NeurIPS 2025). Public numeric scores; leaderboard licence not stated (code MIT not applied; CC BY-NC trajectories not used).