agents benchmark
FocusBench Leaderboard
FocusBench is an internal personal agent evaluation across housing, travel, IT, and finance.
Updated Oct 23, 2026
Models4
Model coverage4
MetricScore
EvidenceB
FocusBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score54.20% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelME | Score54.20% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score44.90% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score44.90% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
FocusBench Highlights
The leading models and scores on this benchmark.
FocusBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FocusBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FocusBench?
What FocusBench measures and how its scores work.
FocusBench is a benchmark for evaluating personal agents across housing, travel, IT, and finance.
It measures persistence through blockers and adaptation across interactions and changing environments using the Score metric as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FocusBench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FocusBench.
Which model scores highest on FocusBench?
Muse Wonder Full is currently ranked first with 54.20%.
What are the top three models on FocusBench?
The current leaders are Muse Wonder Full (54.20%), Muse Wonder Full (54.20%), and Muse Wonder (44.90%).
Which FocusBench model has the lowest official input price?
Muse Wonder has the lowest matched official input price at $4.0 input / $20 output per 1M tokens.
Which models are fastest among FocusBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.