← PEICO
Anthropic

Claude Opus 4.8 (no thinking)

k=1

anthropic/claude-opus-4-8

Score
92.5
Rank
#3 of 11
Trials
80
Agent cost
$11.24
$ / task
$0.14
Median time
43s
Cases
All 80 tasks × 1 trial. Open a case to read the full conversation and grader verdicts