Benchmark
OSWorld 2.0
OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks. Each task is an end-to-end…
- Modality
- multimodal
- Categories
- multimodal, general, agents, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 5
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Opus 5 | Anthropic | 0.706 | 2026-07-24 | evidence |
| Gemini 3.7 Flash | 0.479 | 2026-08-13 | evidence | |
| GPT-5.6 Luna | OpenAI | 0.456 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.626 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.502 | 2026-07-09 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.