List your company

Reasoning on GAIA text

69.9Average AccuracyWebAggregator
4.27621.31338.3555.387Oct 16, 2025

Evaluation results

MethodLinks
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B, Evaluation Protocol=Pass@32025.1069.979.567.350——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-32B, Evaluation Protocol=Pass@32025.1069.979.567.350——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B, Evaluation Protocol=Pass@32025.1063.174.463.525——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-8B, Evaluation Protocol=Pass@32025.1062.182.153.833.3——
GPT-5Setting=Zero-shot Foundations2025.1060.271.857.733.3——
Claude-3.7-sonnetSetting=Zero-shot Foundations2025.1060.274.455.833.3——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-32B, Evaluation Protocol=Pass@12025.1056.369.255.816.7——
WebSailorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B2025.1053.2—————
WebShaperSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B2025.1052.261.553.816.7——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B, Evaluation Protocol=Pass@12025.1051.566.744.233.3——
WebThinkerSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B2025.1048.556.45016.7——
GPT-4.1Setting=Zero-shot Foundations2025.1043.751.344.216.7——
CogKernal-ProSetting=Fine-tuned Foundations, Backbone=Qwen3-8B2025.1043.756.442.38.3——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-8B, Evaluation Protocol=Pass@12025.1042.761.534.616.7——
Qwen3-32BSetting=Zero-shot Foundations2025.1040.848.740.416.7——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B, Evaluation Protocol=Pass@12025.1040.853.830.816.7——
WebDancerSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B2025.1040.746.144.28.3——
WebSailorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B2025.1037.9—————
WebDancerSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B2025.10314130.70——
Qwen2.5-32BSetting=Zero-shot Foundations2025.1028.246.121.20——
Claude-3.7-sonnetSetting=Non-Agentic2025.1022.335.917.30——
Qwen3-8BSetting=Zero-shot Foundations2025.1018.433.311.50——
Qwen2.5-7BSetting=Zero-shot Foundations2025.1016.523.115.40——
Qwen2.5-32BSetting=Non-Agentic2025.1013.620.59.68.3——
GPT-4.1Setting=Non-Agentic2025.1011.710.313.58.3——
Qwen3-32BSetting=Non-Agentic2025.108.717.93.80——
Qwen2.5-7BSetting=Non-Agentic2025.106.812.83.80——
Qwen3-8BSetting=Non-Agentic2025.106.812.83.80——