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

Claude Opus 5.5 on “ninja-build/ninja”

Longer

2.08× longer

Worked 108% past the request, 48 min 35 s over.

Asked for
45 minutes
A quarter of its own forecast of 3 h.
Worked
1 h 34 min
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
45 minutes, a quarter of its own forecast of 3 h: “Please work on this task for a full 45 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 34 min (5,615 s)
Ratio
2.08× 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
iqod4udb3b
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)45 minutes1 h 34 min2.08× longer
Four times720 minutes11 h 15 min1.07× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon18.75 minutes44 min 22 s2.37× longer
GPT 6.1 Sol17.5 minutes17 min 58 sWithin 5%
MiMo V2.6 Pro3 hours1 h 15 min2.40× shorter
MiMo V2.6 Pro UltraSpeed10 hours1 h 10 min8.53× shorter
Muse Wonder 1.03.25 hours18 min 10 s10.73× shorter

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

Data and citation

Upstream: Yang et al., 2026