Benchmark · Knowledge

USAMO

Updated 2026-04-07
Models tested
1
Top score
97.6
Claude Mythos Preview
Median
97.6
min 97.6
Top-5 spread
σ 0.0
Settled

1 models tested · sorted by score

#ModelScore
1Anthropic logoClaude Mythos Preview97.6

Same category · related evaluations