PaperBench, longest of three requests
GPT 5.6 Sol on “Bridging Data Gaps”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 200 minutes
- Worked
- 3 h 20 min
- Grade
- Score 34.4 of 100
- Judged afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- PaperBench
- Asked for
- 200 minutes: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 3 h 20 min (12,022 s)
- Ratio
- 1.00× the request
- How it ended
- Ended on its own
- Grade
- 0.344
- Replication score: a weighted rubric of pass/fail leaf checks, 0 to 1, after a full reproduction attempt. No official pass rule.
- Score
- 34.4 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- 5x7q3qi7ia
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 12.5 minutes | 6 min 11 s | 2.02× shorter | |
| Middle | 50 minutes | 51 min 15 s | Within 5% | |
| Longest (this run) | 200 minutes | 3 h 20 min | Within 5% | |
| Other agents, longest request | ||||
| GPT 6 Astra | 200 minutes | 3 h 21 min | Within 5% | |
| Claude Fable 5.1 | 200 minutes | 45 min 29 s | 4.40× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Starace et al., 2025