terminal-bench-terminal-bench-2-claude-code-bedrock-baseline-28737497731
PublicRerun job
81 / 81 finished
Started Jul 5, 2026, 10:22 AM · Ran for 2h 20m
81 completed0 errors0 in progress0 pending
Average reward
0.31
Across scored trials
Total tokens
159,390,466
1,967,784 tokens/trial · 98% cache hit
Inference cost
$29.04
$0.36 per finished trial
Sandbox cost
—
Results
Metric: reward
Group by0 groups
Loading results…