Skip to content
Hbench

Terminal-Bench 2.0 on qwen3-coder-480b-a35b-instruct-fp8

89 tasks, 5 attempts, open network. Updated 25 Oct 2026.

Build a run for this board

Ranking

Pass rate by harness, higher is better

Embed this chart

HarnessPass rate
aone-agent1.18.72-pre27.2%95% interval 19.8–35.1

All harnesses

Reading this table

Every harness on this board, in its order
Harnesspass^5RunsLast published
aone-agent1.18.72-pre11.2%13 infra25 Oct 2026run #93