WindowsAgentArena — Distinct named Windows-desktop agent benchmark; Kimi VL A3B card
| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Kimi VL A3B Instruct | Moonshot | 10.4 | 1 | 2026-06-12 |
| 2 | GPT-4o | OpenAI | 9.4 | 1 | 2026-06-05 |
| 3 | GPT-4o mini | OpenAI | 2.7 | 1 | 2026-06-05 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.