Task 3 of 18 in OSWorld
Local event booking QA
Sol 6.1's two runs came closest to the time asked: 10 min 6 s when asked for 8 min 45 s, and 2 h 25 min when asked for 2 h 20 min. Muse Wonder's one run landed furthest: 1 h 52 min when asked for 9 min 30 s.
- Asked for
- 2 min 15 s to 4 h 10 min
- Runs here
- 17
- See Read before quoting below
Every agent on this task
- Astra
- Sol
- Fable
- Opus 5.5
- Argon
- Sol 6.1
- MiMo Pro
- MiMo UltraSpeed
- Muse Wonder
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 |
|---|---|---|---|---|
| Astra | 1 h | 40 min 57 s | 18 min 39 s 1.24× longer asked 15 min | 4 h 13 min Within 5% asked 4 h 10 min |
| Sol | 45 min | 38 min 23 s | 23 min 52 s 1.59× longer asked 15 min | 2 h 47 min 1.50× shorter asked 4 h 10 min |
| Fable | 45 min | 59 min 34 s | 12 min 24 s 1.21× shorter asked 15 min | 1 h 25 min 2.94× shorter asked 4 h 10 min |
| Opus 5.5 | 35 min | 1 h 27 min | 8 min 31 s Within 5% asked 8 min 45 s | 1 h 58 min 1.19× shorter asked 2 h 20 min |
| Argon | 9 min | 51 min 40 s | 2 min 51 s 1.27× longer asked 2 min 15 s | 37 min 37 s Within 5% asked 36 min |
| Sol 6.1 | 35 min | 26 min 19 s | 10 min 6 s 1.15× longer asked 8 min 45 s | 2 h 25 min Within 5% asked 2 h 20 min |
| MiMo Pro | 45 min | 5 h 8 min | 15 min 25 s 1.37× longer asked 11 min 15 s | 9 min 34 s 18.81× shorter asked 3 h |
| MiMo UltraSpeed | 40 min | 4 h 5 min | 38 min 7 s 3.81× longer asked 10 min | 5 h 20 min 2.00× longer asked 2 h 40 min |
| Muse Wonder | 38 min | 3 h 11 min | 1 h 52 min 11.77× longer asked 9 min 30 s | No run |
No runs match these filters.
Runtime is a v1.1 agent’s run with no time asked, and for the paper’s three agents the paper’s estimate from their timed runs.
Read before quoting. 1 run was stopped by AgentTime, so its time is a lower bound. Details
Data and citation
Upstream: Yuan et al., 2026