List your company

Compositional Reasoning on WebAggregatorQA

70.8Level-1 ScoreWebAggregator
1.53619.51837.555.482Oct 16, 2025

Evaluation results

MethodLinks
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B, Evaluation Protocol=Pass@32025.1070.822.219.428.9——
Claude-3.7-sonnetSetting=Zero-shot Foundations2025.1066.725.311.128.3——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-32B, Evaluation Protocol=Pass@32025.1066.735.413.935.2——
GPT-4.1Setting=Zero-shot Foundations2025.1062.422.211.125.8——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-8B, Evaluation Protocol=Pass@32025.1062.421.211.125.2——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-32B, Evaluation Protocol=Pass@12025.1062.424.28.326.4——
GPT-5Setting=Zero-shot Foundations2025.1058.324.522.228.9——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B, Evaluation Protocol=Pass@32025.1054.222.219.426.4——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-32B, Evaluation Protocol=Pass@12025.1054.215.211.120.1——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen3-8B, Evaluation Protocol=Pass@12025.1054.211.15.616.4——
Qwen3-32BSetting=Zero-shot Foundations2025.1045.810.15.614.5——
WebAggregatorSetting=Fine-tuned Foundations, Backbone=Qwen2.5-7B, Evaluation Protocol=Pass@12025.1037.511.18.314.5——
Qwen3-8BSetting=Zero-shot Foundations2025.1030.85.15.69.4——
Qwen2.5-7BSetting=Zero-shot Foundations2025.1027.33.42.86.3——
Qwen2.5-32BSetting=Zero-shot Foundations2025.102510.15.611.3——
Claude-3.7-sonnetSetting=Non-Agentic2025.1018.55.12.86.8——
GPT-4.1Setting=Non-Agentic2025.1015.442.85.6——
Qwen3-32BSetting=Non-Agentic2025.108.3101.9——
Qwen2.5-7BSetting=Non-Agentic2025.104.2101.3——
Qwen2.5-32BSetting=Non-Agentic2025.104.2101.3——
Qwen3-8BSetting=Non-Agentic2025.104.212.81.9——