ProgramBench, AgentTime v1.1, asked for four times its own forecast

Claude Opus 5.5 on “mookid/diffr”

Shorter

1.99× shorter

Stopped at 50% of the time asked, 3 h 59 min short.

Asked for
480 minutes
Four times its own forecast of 2 h.
Worked
4 h 1 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
480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 h 1 min (14,486 s)
Ratio
0.50× 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
ziluzyghq7
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
Quarter30 minutes3 h 36 min7.20× longer
Four times (this run)480 minutes4 h 1 min1.99× shorter
Other agents, four times their own forecast
Gemini 4 Argon180 minutes1 h 26 min2.08× shorter
GPT 6.1 Sol260 minutes4 h 20 minWithin 5%
MiMo V2.6 Pro16 hours1 h 52 min8.54× shorter
MiMo V2.6 Pro UltraSpeed28 hours1 h 13 min22.87× shorter
Muse Wonder 1.020 hours17 min 49 s67.34× shorter

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

Data and citation

Upstream: Yang et al., 2026