ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “lfos/calcurse”

Shorter

4.57× shorter

Stopped at 22% of the time asked, 32 min 14 s short.

Asked for
41.25 minutes
A quarter of its own forecast of 2 h 45 min.
Worked
9 min 1 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Benchmark
ProgramBench
Asked for
41.25 minutes, a quarter of its own forecast of 2 h 45 min: “Please work on this task for a full 41.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 1 s (541 s)
Ratio
0.22× the request
How it ended
Ended on its own
Grade
Not graded
Clock tool
The agent could call a wall-clock tool to read the current time.
Wording
The paper's standard sentence, sent in AgentTime v1.1.
Run id
5szqrefdnh
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter (this run)41.25 minutes9 min 1 s4.57× shorter
Four times660 minutes10 h 35 minWithin 5%
Other agents, a quarter of their own forecast
Gemini 4 Argon22.5 minutes43 min 13 s1.92× longer
GPT 6.1 Sol22.5 minutes23 min 3 sWithin 5%
MiMo V2.6 Pro3.75 hours53 min 52 s4.18× shorter
MiMo V2.6 Pro UltraSpeed2.25 hours1 h 21 min1.66× shorter
Muse Wonder 1.07.5 hours42 min 59 s10.47× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Yang et al., 2026