Information-seeking on Xbench-DS
75Success RateQwen3-VL-30B-A3B-ICA
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-30B-A3B-ICATools=Search & Fetch (snap.)2026.02 | 75 | |
| OpenAI-o32026.02 | 66.7 | |
| Claude-4-Sonnet2026.02 | 64.6 | |
| Qwen3-VL-8B-ICATools=Search & Fetch (snap.)2026.02 | 58 | |
| C-GRPOTools=Search & Fetch (text)2026.02 | 57.7 | |
| WebExplorer-8BTools=Search & Fetch (text)2026.02 | 53.7 | |
| WebSailor-32BTools=Search & Fetch (text)2026.02 | 53.3 | |
| DeepDiver-V2-38BTools=Search & Fetch (text)2026.02 | 53 | |
| DeepDive-32BTools=Search & Fetch (text)2026.02 | 51.8 | |
| Kimi-K2-Instruct-1TTools=Search & Fetch (text)2026.02 | 50 | |
| ASearcher-Web-32BTools=Search & Fetch (text)2026.02 | 42.1 | |
| InfoAgentTools=Search & Fetch (text)2026.02 | 40.4 | |
| WebDancer-QwQ-32BTools=Search & Fetch (text)2026.02 | 38.3 | |
| DeepDive-9BTools=Search & Fetch (text)2026.02 | 38 | |
| WebShaper-QwQ-32BTools=Search & Fetch (text)2026.02 | 35 | |
| WebSailor-7BTools=Search & Fetch (text)2026.02 | 34.3 | |
| MiroThinker-14B-DPO-v0.1Tools=Search & Fetch (text)2026.02 | 30 | |
| Qwen3-14BTools=Search & Fetch (text)2026.02 | 20 |