Fara1.5 – A family of frontier computer use agent models
Update __init__.py
Corby Rossetb0030f7abe09
diff --git a/webeval/src/webeval/benchmarks/__init__.py b/webeval/src/webeval/benchmarks/__init__.pyindex 5e4af93..fd92088 100644--- a/webeval/src/webeval/benchmarks/__init__.py+++ b/webeval/src/webeval/benchmarks/__init__.py@@ -1,39 +1,9 @@-# from .assistantbench.assistantbench import AssistantBenchBenchmark-# from .custom.custom import CustomBenchmark-# from .gaia.gaia import GaiaBenchmarkfrom .webvoyager.webvoyager import WebVoyagerBenchmark-# from .mdm2w.mdm2w import MultimodalM2WBenchmark-# from .aurora.aurora import AuroraBenchmarkfrom .om2w.om2w import OnlineM2WBenchmarkfrom .webtailbench.webtailbench import WebTailBenchBenchmark-# from .holdout.holdout import HoldoutBenchmark-# from .deepshop.deepshop import DeepShopBenchmark-# from .browsecomp.browsecomp import BrowseCompBenchmark-# from .screenspot.screenspot_v1 import ScreenspotV1Benchmark-# from .screenspot.screenspot_v2 import ScreenspotV2Benchmark-# from .screenspot.screenspot_pro import ScreenspotProBenchmark-# from .instruction_following.instruction_following import InstructionFollowingBenchmark-# from .instruction_following.agent_harm import AgentHarmBenchmark-# from .instruction_following.visualwebbench_webqa import VisualWebBenchWebQA-# from .realeval.realeval import RealEvalBenchmark__all__ = [- # "AssistantBenchBenchmark",- # "CustomBenchmark",- # "GaiaBenchmark","WebVoyagerBenchmark",- # "MultimodalM2WBenchmark",- # "AuroraBenchmark","OnlineM2WBenchmark",- "WebTailBenchBenchmark",- # "HoldoutBenchmark",- # "DeepShopBenchmark",- # "BrowseCompBenchmark",- # "ScreenspotV1Benchmark",- # "ScreenspotV2Benchmark",- # "ScreenspotProBenchmark",- # "InstructionFollowingBenchmark",- # "AgentHarmBenchmark",- # "VisualWebBenchWebQA",- # "RealEvalBenchmark"+ "WebTailBenchBenchmark"]