gpt-5.6-luna-no-cheat-instruction__scrubbed__413ec154-36fb-46f4-a0b2-2111e1c65501

Created by Kobe Chen
||Owned by Terminal-Bench
PublicRerun job
445 / 445 finished
Started Jul 11, 2026, 7:57 PM · Ran for 1h 32m
429 completed16 timeouts0 errors0 in progress0 pending
Average reward
0.77
Across scored trials
Total tokens
1,427,219,692
3,207,235 tokens/trial · 97% cache hit
Inference cost
$241.45
$0.54 per finished trial
Sandbox cost
—

Results

Metric: reward
Group by0 groups
Loading results…