List your company
ResearchFormerly WizWand

Web Search on BrowseComp-Plus

53.02Pass@3AdaCoM
9.901621.095832.2943.4842May 29, 2026
Updated 5mo ago

Evaluation results

MethodLinks
AdaCoMBackbone=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0553.02
AdaCoMBackbone=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0552
MemActBackbone=Qwen3-Max, CM Model=agent itself, CM Trained=×2026.0550.67
AdaCoMBackbone=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0550.67
AdaCoMBackbone=Average, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0548.92
MemActBackbone=GLM-4.5-Air, CM Model=agent itself, CM Trained=×2026.0546
SumCoMBackbone=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0545.33
SumAgentBackbone=Kimi-K2-Instruct, CM Model=agent itself, CM Trained=×2026.0544.67
ReActBackbone=GLM-4.5-Air, CM Model=-, CM Trained=-2026.0544.67
AdaCoM w/o train.Backbone=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0542.75
SumCoMBackbone=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0542.67
SumCoMBackbone=Average, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0540.33
AdaCoMBackbone=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0539.97
SumAgentBackbone=Qwen3-Max, CM Model=agent itself, CM Trained=×2026.0538.67
ReActBackbone=Qwen3-Max, CM Model=-, CM Trained=-2026.0538
SumCoMBackbone=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0537.33
MemActBackbone=Average, CM Model=agent itself, CM Trained=×2026.0537.33
MemActAgent=Qwen3-Max, CM Model=agent itself, CM Trained=×2026.0537.33
AdaCoMAgent=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0536.67
AdaCoMAgent=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0536.2
SumCoMBackbone=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0536
AdaCoMAgent=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0535.33
ReActBackbone=Average, CM Model=-, CM Trained=-2026.0534.67
SumCoMAgent=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0533.78
AdaCoMAgent=Avg., CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0533.6
AdaCoM w/o train.Backbone=Average, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0533.45
SumAgentBackbone=Average, CM Model=agent itself, CM Trained=×2026.0533
AdaCoM w/o train.Backbone=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0532.67
ReActAgent=GLM-4.5-Air, CM Model=–, CM Trained=–2026.0532.56
SumCoMAgent=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0532.22
MemActAgent=GLM-4.5-Air, CM Model=agent itself, CM Trained=×2026.0532
AdaCoM w/o train.Backbone=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0530.67
SumAgentAgent=Kimi-K2-Instruct, CM Model=agent itself, CM Trained=×2026.0530.44
MemActBackbone=Kimi-K2-Instruct, CM Model=agent itself, CM Trained=×2026.0530
SumCoMAgent=Avg., CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0529.39
ReActBackbone=Kimi-K2-Instruct, CM Model=-, CM Trained=-2026.0529.33
SumAgentBackbone=DeepSeek-V3, CM Model=agent itself, CM Trained=×2026.0528.67
AdaCoM w/o train.Agent=Kimi-K2-Instruct, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0528.02
ReActAgent=Qwen3-Max, CM Model=–, CM Trained=–2026.0527.78
AdaCoM w/o train.Backbone=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0527.7
ReActBackbone=DeepSeek-V3, CM Model=-, CM Trained=-2026.0526.67
SumAgentAgent=Qwen3-Max, CM Model=agent itself, CM Trained=×2026.0526.67
SumCoMAgent=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0526.44
AdaCoMAgent=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0526.19
MemActAgent=Avg., CM Model=agent itself, CM Trained=×2026.0525.72
SumCoMAgent=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=✓2026.0525.11
ReActAgent=Avg., CM Model=–, CM Trained=–2026.0524.17
MemActBackbone=DeepSeek-V3, CM Model=agent itself, CM Trained=×2026.0522.67
SumAgentAgent=Avg., CM Model=agent itself, CM Trained=×2026.0522.06
AdaCoM w/o train.Agent=Avg., CM Model=Qwen3-4B-Inst., CM Trained=×2026.0522.01
AdaCoM w/o train.Agent=GLM-4.5-Air, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0521.33
AdaCoM w/o train.Agent=Qwen3-Max, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0521.11
SumAgentBackbone=GLM-4.5-Air, CM Model=agent itself, CM Trained=×2026.0520
SumAgentAgent=DeepSeek-V3, CM Model=agent itself, CM Trained=×2026.0519.56
ReActAgent=Kimi-K2-Instruct, CM Model=–, CM Trained=–2026.0518.56
ReActAgent=DeepSeek-V3, CM Model=–, CM Trained=–2026.0517.78
AdaCoM w/o train.Agent=DeepSeek-V3, CM Model=Qwen3-4B-Inst., CM Trained=×2026.0517.57
MemActAgent=Kimi-K2-Instruct, CM Model=agent itself, CM Trained=×2026.0516.89
MemActAgent=DeepSeek-V3, CM Model=agent itself, CM Trained=×2026.0516.67
SumAgentAgent=GLM-4.5-Air, CM Model=agent itself, CM Trained=×2026.0511.56