CORE-Bench v1.1, shortest of three requests

GPT 5.6 Sol on “Reproduce article and script-availability results across linguistics”

Longer

1.08× longer

Worked 8% past the request, 38 s over.

Asked

Worked

Safety cutoff 4 h 10 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: CORE-Bench v1.1
Task: Reproduce article and script-availability results across linguistics
Asked for: 8 minutes: “Please work on this task for a full 8 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 8 min 38 s (518 s)
Ratio: 1.08× the request
How it ended: Ended on its own
Grade: Passed; It got every answer right. The grader returned 1. Pass rule: Every answer correct, with numbers inside a 95% prediction interval.
Score: 100 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: rih5xrlpxd
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)	8 minutes	8 min 38 s	1.08× longer
Middle	30 minutes	33 min 42 s	1.12× longer
Longest	125 minutes	8 min 15 s	15.14× shorter
Other agents, shortest request
GPT 6 Astra	8 minutes	8 min 24 s	Within 5%
Claude Fable 5.1	8 minutes	5 min 58 s	1.34× shorter

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

Data and citation