CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast

Claude Opus 5.5 on “Run a continuous-time intelligent-reflecting-surface propagation model”

Shorter

2.03× shorter

Stopped at 49% of the time asked, 24 min 19 s short.

Asked for
48 minutes
Four times its own forecast of 12 min.
Worked
23 min 41 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Asked for
48 minutes, four times its own forecast of 12 min: “Please work on this task for a full 48 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
23 min 41 s (1,421 s)
Ratio
0.49× 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
gmpcgal76q
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
Quarter3 minutes24 min 57 s8.32× longer
Four times (this run)48 minutes23 min 41 s2.03× shorter
Other agents, four times their own forecast
Gemini 4 Argon840 seconds16 min 22 s1.17× longer
GPT 6.1 Sol40 minutes40 min 58 sWithin 5%
MiMo V2.6 Pro180 minutes23 min 2 s7.81× shorter
MiMo V2.6 Pro UltraSpeed240 minutes17 min 41 s13.57× shorter
Muse Wonder 1.0120 minutes2 min 59 s40.27× shorter

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

Data and citation

Upstream: Nadgir et al., 2026