Task 5 of 12 in BrowseComp
BrowseComp question 5
Sol 6.1's two runs followed the time asked: 5 min 10 s when asked for 5 min, and 1 h 21 min when asked for 1 h 20 min. MiMo UltraSpeed's two runs landed furthest: 3 min 29 s when asked for 8 min 45 s, and 17 min 51 s when asked for 2 h 20 min.
- Asked for
- 1 min 15 s to 2 h 20 min
- Runs here
- 12
- 6 agents
Every agent on this task
- 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 |
|---|---|---|---|---|
| Opus 5.5 | 22 min | 5 min 32 s | 5 min 52 s 1.07× longer asked 5 min 30 s | 49 min 18 s 1.79× shorter asked 1 h 28 min |
| Argon | 5 min | 1 min 1 s | 1 min 29 s 1.19× longer asked 1 min 15 s | 20 min 15 s Within 5% asked 20 min |
| Sol 6.1 | 20 min | 2 min 18 s | 5 min 10 s Within 5% asked 5 min | 1 h 21 min Within 5% asked 1 h 20 min |
| MiMo Pro | 18 min | 22 min 54 s | 15 min 16 s 3.39× longer asked 4 min 30 s | 29 min 6 s 2.47× shorter asked 1 h 12 min |
| MiMo UltraSpeed | 35 min | 21 min 13 s | 3 min 29 s 2.51× shorter asked 8 min 45 s | 17 min 51 s 7.84× shorter asked 2 h 20 min |
| Muse Wonder | 24 min | 38 s | 6 min 23 s 1.06× longer asked 6 min | 1 h 38 min Within 5% asked 1 h 36 min |
No runs match these filters.
Runtime is each agent’s run with no time asked.
Data and citation
Upstream: Wei et al., 2025