Skip to content

armgit / cua

Public Imported from GitHub
0

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

added base models to benchmark

Dillon DuPont8eb662bf4dee
diff --git a/libs/python/agent/benchmarks/utils.py b/libs/python/agent/benchmarks/utils.py
index 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 asyncio
import base64
import 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"),