OSWorld 2.0
- OpenAI
Results
| Model | Score | Source | Human-verified |
|---|---|---|---|
| Gemini 4 Argon30 Sep 2026 · Google | 69.2% | Gemini 4 Argon: our next era of frontier intelligenceSource image | Yes |
| GPT-6 Astra3 Sep 2026 · OpenAI | 72.6% | GPT-6 Astra: A new generation of intelligencetask release v2026.08.08 | Yes |
Benchmark
huggingface.coHigher is better