TB 4.0.0 - GLM-5.3 / Claude Code

Created by Ryan Marten
||Owned by Ryan Marten
PublicRerun job
330 / 330 finished
Started Aug 26, 2026, 3:16 PM · Running for 0s
322 completed8 errors0 in progress0 pending
Average reward
0.42
Across scored trials
Total tokens
8,677,039,373
26,294,059 tokens/trial · 98% cache hit
Inference cost
$2,727.63
$8.27 per finished trial
Sandbox cost
—

Results

Metric: reward
Group by0 groups
Loading results…