PaperBench, shortest of three requests

GPT 5.6 Sol on “Bridging Data Gaps”

Shorter

2.02× shorter

Stopped at 49% of the time asked, 6 min 19 s short.

Asked

Worked

Safety cutoff 6 h 40 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: PaperBench
Task: Bridging Data Gaps
Asked for: 12.5 minutes: “Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 6 min 11 s (371 s)
Ratio: 0.49× the request
How it ended: Ended on its own
Grade: 0.073; Replication score: a weighted rubric of pass/fail leaf checks, 0 to 1, after a full reproduction attempt. No official pass rule.
Score: 7.3 of 100; Judged afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: 2u3g5jvx2x
Data release: 26 Sep 2026

The other requests for GPT 5.6 Sol on this task, and the other agents at this request
Sol on this task	Asked	Worked	Result
Shortest (this run)	12.5 minutes	6 min 11 s	2.02× shorter
Middle	50 minutes	51 min 15 s	Within 5%
Longest	200 minutes	3 h 20 min	Within 5%
Other agents, shortest request
GPT 6 Astra	12.5 minutes	12 min 39 s	Within 5%
Claude Fable 5.1	12.5 minutes	5 min 18 s	2.36× shorter

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

Data and citation