Terminal Bench 4.0 GPT-6.1-Sol Max

Created by Sam Vance
||Owned by Harbor
PublicRerun job
330 / 330 finished
Started Sep 30, 2026, 12:43 AM · Ran for 21h 41m
327 completed3 timeouts0 errors0 in progress0 pending
Average reward
0.59
Across scored trials
Total tokens
1,459,936,514
4,424,050 tokens/trial · 95% cache hit
Inference cost
$634.24
$1.92 per finished trial
Sandbox cost
$562.82

Results

Metric: reward
Group by0 groups
Loading results…