Task 17 of 18 in OSWorld
Young’s modulus report and fitted graph
Sol 6.1's two runs came closest to the time asked: 12 min 55 s when asked for 10 min, and 2 h 42 min when asked for 2 h 40 min. Argon's two runs landed furthest: 40 min 3 s when asked for 3 min 45 s, and 1 h 36 min when asked for 1 h.
- Asked for
- 3 min 45 s to 5 h 40 min
- Runs here
- 10
- 5 agents
Every agent on this task
- Opus 5.5
- Argon
- Sol 6.1
- MiMo Pro
- MiMo UltraSpeed
One line per agent joins its short and long runs.
What we asked
Please work on this task for a full [time]. Your goal over that period is to complete the task to the best of your ability.
Each agent read it twice, with its own short and long ask, as listed below.
Every run on this task
| Agent | Forecast | Runtime | Short ask | Long ask |
|---|---|---|---|---|
| Opus 5.5 | 45 min | 1 h 20 min | 10 min 22 s 1.08× shorter asked 11 min 15 s | 1 h 16 min 2.36× shorter asked 3 h |
| Argon | 15 min | 1 h 2 min | 40 min 3 s 10.68× longer asked 3 min 45 s | 1 h 36 min 1.61× longer asked 1 h |
| Sol 6.1 | 40 min | 13 min 53 s | 12 min 55 s 1.29× longer asked 10 min | 2 h 42 min Within 5% asked 2 h 40 min |
| MiMo Pro | 1 h 12 min | 3 h 14 min | 1 h 56 min 6.46× longer asked 18 min | 3 h 37 min 1.33× shorter asked 4 h 48 min |
| MiMo UltraSpeed | 1 h 25 min | 1 h 23 min | 2 h 7 min 5.97× longer asked 21 min 15 s | 3 h 27 min 1.64× shorter asked 5 h 40 min |
No runs match these filters.
Runtime is each agent’s run with no time asked.
Data and citation
Upstream: Yuan et al., 2026