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

Claude Opus 5.5 on “ariga/atlas”

Within 5%

Within 5%

Worked 95% of the time asked, within 5% of it.

Asked for
840 minutes
Four times its own forecast of 3 h 30 min.
Worked
13 h 22 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
840 minutes, four times its own forecast of 3 h 30 min: “Please work on this task for a full 840 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
13 h 22 min (48,104 s)
Ratio
0.95× 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
exdx22oka5
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
Quarter52.5 minutes41 min 47 s1.26× shorter
Four times (this run)840 minutes13 h 22 minWithin 5%
Other agents, four times their own forecast
Gemini 4 Argon300 minutes1 h 18 min3.86× shorter
GPT 6.1 Sol400 minutes6 h 45 minWithin 5%
MiMo V2.6 Pro120 hours58 min 13 s123.67× shorter
MiMo V2.6 Pro UltraSpeed80 hours1 h 23 min57.76× shorter
Muse Wonder 1.072 hours2 min 10 s1990.78× shorter

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

Data and citation

Upstream: Yang et al., 2026