Web Research on WideSearch
74.2AccuracyAgentFugue
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AgentFugueArchitecture=Multi-Agent, Backbone=DeepSeek-v4-Flash, Team size=22026.05 | 74.2 | 65 | |
| Kimi-K2.5Architecture=Single-Agent ReAct, Backbone=-2026.05 | 72.7 | — | |
| Swarm-Multi-AgentArchitecture=Multi-Agent, Backbone=DeepSeek-v4-Flash, Team size=22026.05 | 72.7 | 57.6 | |
| AgentFugueArchitecture=Multi-Agent, Backbone=Qwen3.5-35B-A3B, Team size=22026.05 | 72.3 | 54.4 | |
| Swarm-Multi-AgentArchitecture=Multi-Agent, Backbone=Qwen3.5-35B-A3B, Team size=22026.05 | 70.4 | 49 | |
| DeepSeek-v4-FlashArchitecture=Single-Agent ReAct, Backbone=-2026.05 | 69.7 | 56 | |
| Naive-Multi-AgentArchitecture=Multi-Agent, Backbone=DeepSeek-v4-Flash, Team size=22026.05 | 69.3 | 57.3 | |
| Naive-Multi-AgentArchitecture=Multi-Agent, Backbone=Qwen3.5-35B-A3B, Team size=22026.05 | 68.9 | 48.5 | |
| Qwen3.5-35B-A3BArchitecture=Single-Agent ReAct, Backbone=-2026.05 | 65.6 | 45.2 | |
| GLM-4.7Architecture=Single-Agent ReAct, Backbone=-2026.05 | 65.4 | 48.7 | |
| AgentFoldArchitecture=Single-Agent DeepResearch, Backbone=Qwen3-30B-A3B2026.05 | 62.1 | — |