multimodal benchmark
OSWorld 2.1 (strict) Leaderboard
OSWorld 2.1 (strict) reports the strict pass rate for OSWorld 2.1 tasks.
Updated Oct 23, 2026
Models6
Model coverage6
MetricScore
EvidenceB
OSWorld 2.1 (strict) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score43.50% | Percentile100.00% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelME | Score39.40% | Percentile80.00% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score39.40% | Percentile60.00% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelAN | Score37.10% | Percentile40.00% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelME | Score34.30% | Percentile20.00% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelME | Score34.30% | Percentile0.00% | Participants6 | EvidenceC | Evaluated |
OSWorld 2.1 (strict) Highlights
The leading models and scores on this benchmark.
OSWorld 2.1 (strict) Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OSWorld 2.1 (strict)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is OSWorld 2.1 (strict)?
What OSWorld 2.1 (strict) measures and how its scores work.
OSWorld 2.1 (strict) is a multimodal benchmark metric for OSWorld 2.1.
It measures the fraction of tasks where every graded checkpoint is satisfied, reported as a ratio; it is separate from the OSWorld 2.1 partial-credit score and OSWorld 2.0.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OSWorld 2.1 (strict)
- Modality
- multimodal
- Primary category
- multimodal
- 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 OSWorld 2.1 (strict).
Which model scores highest on OSWorld 2.1 (strict)?
Claude Sonnet 5.5 is currently ranked first with 43.50%.
What are the top three models on OSWorld 2.1 (strict)?
The current leaders are Claude Sonnet 5.5 (43.50%), Muse Wonder Full (39.40%), and Muse Wonder Full (39.40%).
Which OSWorld 2.1 (strict) model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among OSWorld 2.1 (strict) results?
The fastest matched records are Claude Sonnet 5.5 (42.00 tok/s via Anthropic).
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.