List your company
ResearchFormerly WizWand

Textual long-horizon complex reasoning on BrowseComp

85.9ScoreGemini-3.1-Pro-Preview
-0.10822.22144.5566.879Jun 13, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Gemini-3.1-Pro-PreviewSize=-, Train=-2026.0685.9
Qwen3.5-397BSize=397B, Train=-2026.0678.6
Doubao-2.0-ProSize=-, Train=-2026.0677.3
MiniMax-M2.7Size=230B, Train=-2026.0676.1
GLM-5Size=744B, Train=-2026.0675.9
Kimi-K2.5Size=1T, Train=-2026.0674.9
Claude-4.6-Sonnet-ThinkingSize=-, Train=-2026.0674.7
MiroThinker-1.7Size=235B, Train=Mid/SFT/RL2026.0674
MiroThinker-1.7-miniSize=30B, Train=Mid/SFT/RL2026.0667.9
GPT-5.2Size=-, Train=-2026.0665.8
DeepSeek-V3.2Size=671B, Train=-2026.0651.4
Tongyi-DeepResearchSize=30B, Train=Mid/SFT/RL2026.0643.4
REDSearcherSize=30B, Train=Mid/SFT/RL2026.0642.1
S1-DeepResearchSize=32B, Train=SFT2026.0636.7
OpenSeeker-v1Size=30B, Train=SFT2026.0629.5
OpenResearcherSize=30B, Train=SFT2026.0626.3
Qwen3-235BSize=235B, Train=-2026.0611.5
Qwen3-32BSize=32B, Train=-2026.063.2