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

GPT 6.1 Sol on “Challenges in Training PINNs: A Loss Landscape Perspective”

Within 5%

Within 5%

Worked 100% of the time asked, within 5% of it.

Asked for
442 minutes
Four times its runtime with no time asked (1 h 51 min).
Worked
7 h 22 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
Asked for
442 minutes, four times its runtime with no time asked (1 h 51 min): “Please work on this task for a full 442 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 h 22 min (26,544 s)
Ratio
1.00× 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
e7oncz35of
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
Quarter27.6 minutes27 min 51 sWithin 5%
Four times (this run)442 minutes7 h 22 minWithin 5%
Other agents, four times their own runtime
Claude Opus 5.555.4 hours16 h 19 min3.40× shorter
Gemini 4 Argon253 minutes2 h 21 min1.80× shorter
MiMo V2.6 Pro UltraSpeed35 hours12 h 53 min2.72× shorter

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

Data and citation

Upstream: Starace et al., 2025