Terminal-Bench 4.0.0 · Fable 5.1 / Claude Code
PublicRerun job
330 / 330 finished
Started Sep 1, 2026, 6:38 PM · Ran for 17h 21m
323 completed7 errors0 in progress0 pending
Average reward
0.58
Across scored trials
Total tokens
2,746,221,560
8,321,884 tokens/trial · 92% cache hit
Total cost
$6,243.50
$18.92 per finished trial
Results
Metric: reward
Group by0 groups
Loading results…