Benchmark 10 of 18, 12 tasks, asked for 30 s to 5 h
BrowseComp
Hard-to-find facts on the live web: each question has a short answer that takes many searches to pin down.
By agent
| Rank | Agent | Within 5%0.95× to 1.05× of the request | Where runs ended, from a tenth of the time asked to ten times it | Timing erroron this benchmark | Scoreout of 100 |
|---|---|---|---|---|---|
| 1 | GPT 6.1 SolCodex | 63%15 of 24 runs | 1.08× | 83.312 graded | |
| 2 | Gemini 4 ArgonAntigravity CLI | 33%8 of 24 runs | 1.33× | 75.012 graded | |
| 3 | Muse Wonder 1.0Muse Code | 21%5 of 24 runs | 2.77× | 75.012 graded | |
| 4 | Claude Opus 5.5Claude Code | 17%4 of 24 runs | 1.75× | 75.012 graded | |
| 5 | MiMo V2.6 ProMiMo Code | 0%0 of 24 runs | 3.90× | 66.712 graded | |
| 6 | MiMo V2.6 Pro UltraSpeedMiMo Code | 0%0 of 24 runs | 6.60× | 58.312 graded |
Score is the mean of each agent’s graded runs here, out of 100: its runs with no time asked. How it is measured
Every BrowseComp run
MiMo UltraSpeed's typical run lasted 0.51× the time asked at the short ask and 0.04× at the long one. Sol 6.1's lasted 1.11× and 1.02×.
Hover a mark to read it, click to pin it here.
Showing 144 runs.
The 12 tasks
| Task | Asked for | Opus 5.5 | Argon | Sol 6.1 | MiMo Pro | MiMo UltraSpeed | Muse Wonder |
|---|---|---|---|---|---|---|---|
| Question 1 | 3.5 min to 5 h | Short 6.64×, long 0.58× | Short 1.18×, long 1.00× | Short 1.03×, long 1.01× | Short 3.31×, long 0.31× | Short 0.52×, long 0.06× | Short 1.96×, long 0.95× |
| Question 2 | 45 s to 3.67 h | Short 1.43×, long 1.11× | Short 1.30×, long 1.03× | Short 1.44×, long 1.04× | Short 0.94×, long 0.03× | Short 0.48×, long 0.02× | Short 0.95×, long 0.06× |
| Question 3 | 1.5 min to 4.67 h | Short 11.63×, long 0.87× | Short 1.14×, long 1.01× | Short 1.03×, long 1.01× | Short 1.89×, long 0.06× | Short 1.28×, long 0.09× | Short 2.70×, long 0.22× |
| Question 4 | 2 min to 2.8 h | Short 3.52×, long 1.00× | Short 3.93×, long 1.01× | Short 1.06×, long 1.04× | Short 3.83×, long 0.21× | Short 0.53×, long 0.04× | Short 1.19×, long 0.09× |
| Question 5 | 1.25 min to 2.33 h | Short 1.07×, long 0.56× | Short 1.19×, long 1.01× | Short 1.03×, long 1.01× | Short 3.39×, long 0.40× | Short 0.40×, long 0.13× | Short 1.06×, long 1.02× |
| Question 6 | 45 s to 2.2 h | Short 1.33×, long 1.04× | Short 1.22×, long 1.09× | Short 1.16×, long 1.02× | Short 2.19×, long 0.22× | Short 0.27×, long 0.02× | Short 1.18×, long 0.05× |
| Question 7 | 30 s to 2.33 h | Short 0.88×, long 1.05× | Short 2.77×, long 1.06× | Short 1.32×, long 1.01× | Short 3.30×, long 0.33× | Short 1.64×, long 0.03× | Short 0.56×, long 0.02× |
| Question 8 | 52.5 s to 2.8 h | Short 1.48×, long 0.82× | Short 1.51×, long 1.05× | Short 1.16×, long 1.01× | Short 2.55×, long 0.22× | Short 0.50×, long 0.08× | Short 1.69×, long 0.06× |
| Question 9 | 45 s to 2.33 h | Short 2.64×, long 1.03× | Short 1.90×, long 1.10× | Short 1.11×, long 1.02× | Short 7.68×, long 0.19× | Short 0.73×, long 0.02× | Short 1.02×, long 1.01× |
| Question 10 | 3 min to 4 h | Short 5.81×, long 1.00× | Short 3.20×, long 1.01× | Short 1.08×, long 1.01× | Short 2.46×, long 0.50× | Short 0.63×, long 0.13× | Short 1.55×, long 1.03× |
| Question 11 | 52.5 s to 4.33 h | Short 1.49×, long 0.67× | Short 1.34×, long 1.01× | Short 1.19×, long 1.03× | Short 3.11×, long 0.11× | Short 0.20×, long 0.03× | Short 1.20×, long 0.20× |
| Question 12 | 1 min to 3 h | Short 3.27×, long 1.19× | Short 1.47×, long 1.19× | Short 1.10×, long 1.02× | Short 4.05×, long 0.33× | Short 0.49×, long 0.05× | Short 0.68×, long 0.13× |
No runs match these filters.
Each mark is one run, at its short or its long ask, placed from 0.1× to 10× of the time asked; the pale band is within 5% of it.
About BrowseComp: the prompt, the grader, the source
Every task's prompt ends with the same sentence for every agent, with that agent's own short or long time:
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.
Every run is graded by BrowseComp's own grader, not a scorer AgentTime invented. It reports a score: whether the final answer matches the reference answer, 100 or 0.
- Tasks
- 12
- Asked for
- 30 s to 5 h
- Runs here
- 144
- 6 agents
- Graded as
- whether the final answer matches the reference answer, 100 or 0
- Source
- Wei et al., 2025
- Data release
- 2 Nov 2026
- 17:20 UTC
Data and citation
Upstream: Wei et al., 2025