PaperBench, AgentTime v1.1, asked for four times its runtime with no time asked

GPT 6.1 Sol on “FRE”

Longer

2.00× longer

Worked 100% past the request, 9 h 18 min over.

Asked for
560 minutes
Four times its runtime with no time asked (2 h 20 min).
Worked
18 h 38 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
PaperBench
Task
FRE
Asked for
560 minutes, four times its runtime with no time asked (2 h 20 min): “Please work on this task for a full 560 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
18 h 38 min (67,087 s)
Ratio
2.00× 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
kytc6ci2g5
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter35 minutes35 min 32 sWithin 5%
Four times (this run)560 minutes18 h 38 min2.00× longer
Other agents, four times their own runtime
Claude Opus 5.597.6 hours38 h 3 min2.56× shorter
Gemini 4 Argon606 minutes7 h 22 min1.37× shorter
MiMo V2.6 Pro71.1 hours18 h 50 min3.78× shorter
MiMo V2.6 Pro UltraSpeed25.1 hours17 h 9 min1.46× shorter

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

Data and citation

Upstream: Starace et al., 2025