multimodal benchmark
OSWorld 2.0 Leaderboard
OSWorld 2.0 is a multimodal benchmark of 108 long-horizon, real-world computer-use workflows covering everyday and professional tasks.
Updated Sep 5, 2026
Models11
Model coverage11
MetricScore
EvidenceB
OSWorld 2.0 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score77.90% | Percentile100.00% | Participants11 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score72.60% | Percentile90.00% | Participants11 | EvidenceC | Evaluated |
| Rank03 | ModelAN | Score70.60% | Percentile80.00% | Participants11 | EvidenceC | Evaluated |
| Rank04 | ModelME | Score66.90% | Percentile70.00% | Participants11 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score62.60% | Percentile60.00% | Participants11 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score59.00% | Percentile50.00% | Participants11 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score50.20% | Percentile40.00% | Participants11 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score47.90% | Percentile30.00% | Participants11 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score45.60% | Percentile20.00% | Participants11 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score19.40% | Percentile10.00% | Participants11 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score19.40% | Percentile0.00% | Participants11 | EvidenceC | Evaluated |
OSWorld 2.0 Highlights
The leading models and scores on this benchmark.
OSWorld 2.0 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OSWorld 2.0
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is OSWorld 2.0?
What OSWorld 2.0 measures and how its scores work.
OSWorld 2.0 is a benchmark consisting of 108 end-to-end computer-use workflows that take human users a median of about 1.6 hours.
It measures workflow completion using a binary-completion metric, reported as a Score ratio, for tasks involving dynamic environments, cross-source reasoning, and implicit-state inference.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OSWorld 2.0
- 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 2.0.
Which model scores highest on OSWorld 2.0?
Claude Fable 5.1 is currently ranked first with 77.90%.
What are the top three models on OSWorld 2.0?
The current leaders are Claude Fable 5.1 (77.90%), GPT-6 Astra (72.60%), and Claude Opus 5 (70.60%).
Which OSWorld 2.0 model has the lowest official input price?
Qwen3.8 Flash has the lowest matched official input price at $0.15 input / $0.47 output per 1M tokens.
Which models are fastest among OSWorld 2.0 results?
The fastest matched records are Gemini 3.7 Flash (117.86 tok/s via Google), GPT-5.6 Terra (99.35 tok/s via OpenAI), and Claude Opus 5 (62.88 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.