Terminal Bench 4.0 Claude Sonnet 5.5 Max

Created by Sam Vance
||Owned by Harbor
PublicRerun job
330 / 330 finished
Started Sep 29, 2026, 5:13 PM · Ran for 8h 5m
326 completed0 timeouts4 errors0 in progress0 pending
Average reward
0.62
Across scored trials
Total tokens
19,413,047,384
58,827,416 tokens/trial · 97% cache hit
Inference cost
$7,333.64
$22.22 per finished trial
Sandbox cost
$921.85

Results

Metric: reward
Group by0 groups
Loading results…