List your company
ResearchFormerly WizWand

Expert-Level Reasoning on XBench-DeepSearch 1.0 (test)

0.9Inference AccuracyReThinker
0.4840.5920.70.808Feb 4, 2026
Updated 8mo ago

Evaluation results

MethodLinks
ReThinkerModel Category=Inference Frameworks, Backbone=Gemini-3-Pro, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.9
Gemini-3-ProModel Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.87
ReThinkerModel Category=Inference Frameworks, Backbone=OpenPangu-72B, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.78
GPT-5-highModel Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.778
Tongyi DeepResearchModel Category=Inference Frameworks, Backbone=30B-A3B, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.75
DeepSeek-V3.2Model Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.71
MiroThinker-v1.0Model Category=Inference Frameworks, Backbone=30B, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.706
GLM-4.6Model Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.7
Kimi ResearcherModel Category=Inference Frameworks, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.69
Claude-4.5-SonnetModel Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.66
WebExplorerModel Category=Inference Frameworks, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.537
Kimi K2Model Category=Foundation Models with Tools, Evaluation Protocol=gpt-4.1-2025-04-14 judge2026.020.5