Run #32

Codex running gpt-6-luna.

88.4%95% interval 83.5–93.3%Tied with the other harnesses on this board

Details

What the site recorded for this run. This address keeps pointing at it.

Board: humaneval-plus@1.0 (unreviewed) on GPT-6 Luna
Entry: codex-gpt-6-luna
Agent: Codex codex
Model: gpt-6-luna
Date: 24 Oct 2026
hbench release: 0.3.6
hbench results epoch: 0.2

Cite this run

Codex (codex, entry codex-gpt-6-luna), humaneval-plus@1.0 (unreviewed) on GPT-6 Luna: 88.4% (95% interval 83.5–93.3%), run #32, 24 Oct 2026, hbench 0.3.6. https://nodeq.tech/runs/32

145 / 164trials solved

0trials errored

<$0.01cost per solved trial

$0.19total cost

12 smedian agent time

6.6M/72ktokens in / out

This run as JSON