Skip to content
Hbench
hbench

Terminal-Bench 2.0 on claude-opus-4-5

89 tasks, 1 attempt, open network. Updated 25 Oct 2026.

Build a run for this board

Value

What a task cost each configuration.

$ per solved task

Lower is cheaper. Dollars per task divided by the pass rate.

Embed this chart

Not reported: mux, OpenCode

Tokens per task

Lower is leaner. Input plus output, cached input included.

Embed this chart

HarnessTokens per task
muxReference4,437×1.00
Not reported: OpenCode

Agent time per task

Lower is faster. Agent start to finish; setup and tests left out.

Embed this chart

HarnessTime per task
muxReference7.8 min×1.00
OpenCode9.3 min×1.20

Pass rate against time per task

Up and to the left is better. Not offered: tokens and dollars, which fewer than two rows report.

Embed this chart

0%25%50%75%100%7.5 min8.3 min9.2 min10.0 minAgent time per taskMore time for a lower pass rate than muxmuxversion not recorded · 7.8 min · 58.4%OpenCodeversion not recorded · 9.3 min · 51.7%
  • On the frontier: no other row has a higher pass rate for less time
  • Off the frontier
  • 95% interval of the pass rate
On the frontier, least time first: mux, 7.8 min a task, 58.4%.
  • 2 runs
  • Updated 25 Oct 2026
  • Method