Skip to content
Hbench

Run #63

droid running gpt-5.3-codex.

77.3%95% interval 69.4–84.5%Ranks 1–3 of 4 on this board

Details

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

Board
Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network)
Entry
droid-gpt-5-3-codex
Agent
droid
Model
gpt-5.3-codex
Date
22 Feb 2026
hbench release
converted from another tool's job
hbench results epoch
0.2
Cite this run
droid (droid, entry droid-gpt-5-3-codex), Terminal-Bench 2.0 on GPT-5.3-Codex (5 attempts, open network): 77.3% (95% interval 69.4–84.5%), run #63, 22 Feb 2026. https://nodeq.tech/runs/63
344 / 445trials solved
4.9 minmedian agent time

By category

The share of trials solved in each kind of task.

This run as JSON