OpenGCUA OSWorld-v2 offline GUI CLI partial score: leaderboard
OpenGCUA paper, OSWorld-v2 v2.1 82-task offline subset excluding26 internet tasks. Latest evaluated attempt per task, never best-of selection; failures retained. Source model identities as printed; effort unspecified for aggregate tables. Partial evaluator score and full-task success are separate metrics. Batched GUI+CLI comparison; full-GCUA cells already present in Table2. Metric: Partial score (%). Higher is better. Source: https://arxiv.org/html/2610.22200v1
Metric: Partial score (%). Source: arxiv.org. Saturation forecast: Around June 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 65.7 | #12 |
| 2 | Qwen 3.8 Max | 57.2 | #31 |
| 3 | GLM-5.3 Flash | 55.8 | #62 |
| 4 | DeepSeek V4.1 Flash | 50.9 | #35 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=opengcua-osworld-v2-offline-gui-cli-partial-score · How It Works · Data refreshed daily, snapshot 2026-10-17.