Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
added base models to benchmark
Dillon DuPont8eb662bf4dee
diff --git a/libs/python/agent/benchmarks/utils.py b/libs/python/agent/benchmarks/utils.pyindex aa99184fd2..d7ef444502 100644--- a/libs/python/agent/benchmarks/utils.py+++ b/libs/python/agent/benchmarks/utils.py@@ -3,6 +3,9 @@Shared utilities for ScreenSpot-Pro benchmarking and interactive testing."""+import dotenv+dotenv.load_dotenv()+import asyncioimport base64import os@@ -85,9 +88,12 @@ def get_available_models() -> List[Union[str, ModelProtocol]]:models = [# === ComputerAgent model strings ===+ "openai/computer-use-preview",+ "anthropic/claude-opus-4-20250514",# f"{local_provider}HelloKKMe/GTA1-7B",# f"{local_provider}HelloKKMe/GTA1-32B",- "openai/computer-use-preview+openai/gpt-4o-mini"+ "openai/computer-use-preview+openai/gpt-4o-mini",+ "anthropic/claude-opus-4-20250514+openai/gpt-4o-mini",# === Reference model classes ===# GTA1Model("HelloKKMe/GTA1-7B"),