WildClawBench, longest of three requests
GPT 6 Astra on “Build a Chinese academic homepage from a resume and visual reference”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 25 minutes
- Worked
- 25 min 20 s
- Grade
- Score 69.2 of 100
- Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6 Astra, in Codex
- Benchmark
- WildClawBench
- Asked for
- 25 minutes: “Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 25 min 20 s (1,520 s)
- Ratio
- 1.01× the request
- How it ended
- Ended on its own
- Grade
- 0.692
- Task grader score, 0 to 1 (a model judge only where the task calls for one). No official pass rule.
- Score
- 69.2 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- empug2otr3
- Data release
- 26 Sep 2026
Related runs
| Astra on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 2 min 5 s | 1.39× longer | |
| Middle | 6 minutes | 6 min 11 s | Within 5% | |
| Longest (this run) | 25 minutes | 25 min 20 s | Within 5% | |
| Other agents, longest request | ||||
| GPT 5.6 Sol | 25 minutes | 26 min 6 s | Within 5% | |
| Claude Fable 5.1 | 25 minutes | 7 min 9 s | 3.50× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Ding et al., 2026