Unstructured Information Seeking Question Answering on UIS-QA
27.3AccuracyUIS-Digger (Pangu)
Evaluation results
| Method | Links | |
|---|---|---|
| UIS-Digger (Pangu)crawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=PanGu-38B2026.03 | 27.3 | |
| UIS-Digger (Qwen)crawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=Qwen3-32B2026.03 | 27.3 | |
| Mementocrawl(s)=✓, visual=✓, file=✓, browser=✗, Backbone=O3 + GPT-4.12026.03 | 25.5 | |
| Tongyi-DRcrawl(s)=✓, visual=✗, file=✗, browser=✗, Backbone=TongyiDR-30B-A3B† + GPT-4o2026.03 | 23.6 | |
| GLM-4.5auto-thinking, web searchcrawl(s)=✓, visual=✗, file=-, browser=✓, Backbone=GLM4.5†2026.03 | 11.8 | |
| DoubaoDeepThinkcrawl(s)=-, visual=-, file=-, browser=-, Backbone=Doubao2026.03 | 11.8 | |
| DDv2crawl(s)=✓, visual=✗, file=✗, browser=✗, Backbone=Pangu-38B2026.03 | 8.2 | |
| WebSailorcrawl(s)=✓, visual=✗, file=✗, browser=✗, Backbone=WebSailor-32B + Qwen3-72B2026.03 | 7.3 | |
| MiroThinker v0.1crawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=MiroThinker-32B-DPO + GPT-4.1 +Claude-S3.72026.03 | 7.3 | |
| AWorldcrawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=Gemini-2.5-pro + GPT-4o2026.03 | 5.5 | |
| OWLcrawl(s)=✓, visual=✓, file=✓, browser=✓, Backbone=O3-mini + 4o + Claude-S3.72026.03 | 4.6 | |
| Gemini-2.5-progoogle_searchcrawl(s)=-, visual=-, file=-, browser=-, Backbone=Gemini-2.5-pro2026.03 | 4.5 | |
| Claude-sonnet-4crawl(s)=-, visual=-, file=-, browser=-, Backbone=Claude-S42026.03 | 2.7 | |
| DeepSeek-V3.1crawl(s)=-, visual=-, file=-, browser=-, Backbone=DeepSeek-V3.12026.03 | 1.8 | |
| GPT-5crawl(s)=-, visual=-, file=-, browser=-, Backbone=GPT-52026.03 | 0.9 |