Terminal-Bench 4.0.0 · Opus 5 / Claude Code
PublicRerun job
330 / 330 finished
Started Aug 26, 2026, 6:18 PM · Ran for 24h 22m
324 completed6 errors0 in progress0 pending
Average reward
0.53
Across scored trials
Total tokens
6,593,861,176
19,981,398 tokens/trial · 97% cache hit
Total cost
$6,060.00
$18.36 per finished trial
Results
Metric: reward
Group by0 groups
Loading results…