List your company

General AI assistant tasks on GAIA n=165 (dev)

73.93Average AccuracyOAgent
31.08242.20653.3364.454Aug 1, 2025

Evaluation results

MethodLinks
OAgentAgent Model=Claude-3-7, Paid Tools=Jina Reader, Whisper, Baidu & Bing API, Protocol=Pass@32025.0873.9383.0274.4253.85
ManusAgent Model=Claude, etc., Paid Tools=Unknown2025.0873.386.570.157.7
Cognitive Kernel-ProAgent Model=Claude-3-7, Paid Tools=—, Protocol=Pass@32025.0870.9183.0268.653.85
TraseAgentAgent Model=Claude, Paid Tools=Unknown2025.0870.383.0269.7746.15
OWL-WorkforceAgent Model=Claude-3-7, Paid Tools=Whisper, o3-mini2025.0869.0984.9167.4442.31
Deep ResearchAgent Model=Unknown, Paid Tools=Unknown2025.0867.3674.2969.0647.6
OAgentAgent Model=Claude-3-7, Paid Tools=Jina Reader, Whisper, Baidu & Bing API2025.0866.6777.3666.2846.15
h2oGPTeAgent Model=Claude-3.5, Paid Tools=Unknown2025.0863.6467.9267.4442.31
Smolagents*Agent Model=Claude-3-7, Paid Tools=—, Protocol=Pass@32025.0863.6475.4761.6346.15
Cognitive Kernel-ProAgent Model=Claude-3-7, Paid Tools=—, Protocol=Voting2025.0863.6469.8165.1246.15
OWL-Workforce*Agent Model=Claude-3-7, Paid Tools=w/o whisper2025.0860.6173.5862.7926.92
OWL-RoleplayingAgent Model=4o & o3-mini, Paid Tools=Chunkr, FireCrawl, Whisper, o3-mini2025.0858.1881.1454.6523.08
Cognitive Kernel-ProAgent Model=Claude-3-7, Paid Tools=—2025.0857.5877.3654.6526.92
DesearchAgent Model=GPT-4o, Paid Tools=Unknown2025.0856.9771.758.1423.08
TapeAgentsAgent Model=Claude-3-7, Paid Tools=—2025.0855.7671.753.4930.77
AutoAgentAgent Model=Claude-3-5, Paid Tools=—2025.0855.1571.753.426.92
Smolagents*Agent Model=Claude-3-7, Paid Tools=—, Protocol=Voting2025.0853.9966.0452.3333.33
Smolagents*Agent Model=Claude-3-7, Paid Tools=—2025.0852.160.3854.6526.92
SmolagentsAgent Model=Openai o1, Paid Tools=—2025.0849.754.7253.4926.92
Magnetic-1Agent Model=OpenAI o1, Paid Tools=—2025.0846.0656.646.5123.08
Cognitive Kernel-ProAgent Model=CK-Pro-8B, Paid Tools=—, Protocol=Pass@32025.0838.1850.9438.3711.54
Cognitive Kernel-ProAgent Model=CK-Pro-8B, Paid Tools=—, Protocol=Voting2025.0834.5447.1733.7211.54
Cognitive Kernel-ProAgent Model=CK-Pro-8B, Paid Tools=—2025.0832.7343.432.5611.54