List your company

Information Retrieval on WideSearch 2025

67.81Item F1 Avg@4A-MAPREDUCE
40.19847.366554.53561.7035Feb 1, 2026

Evaluation results

MethodLinks
A-MAPREDUCEBackbone=GPT-5-mini2026.0267.8175.0345.2356.247.512
MASBackbone=Claude Sonnet 4, Thinking Mode=Thinking2026.0262.1773.1338.4952.193.626.5
MASBackbone=Kimi K22026.0261.1570.7236.2249.636.5
Gemini 2.5 ProSystem Category=End-to-End System2026.0259.0567.1736.6345.414.258
Claude Sonnet 4System Category=Single Agent, Thinking Mode=Thinking2026.0257.8966.7331.6941.92.255
MASBackbone=Gemini 2.5 Pro2026.0257.4266.3133.4744.6426.5
MASBackbone=OpenAI o32026.0257.3168.9337.850.525.129.5
Flash-searcherBackbone=GPT-5-mini2026.0254.9967.4934.4247.186.410
MASBackbone=Doubao-Seed-1.6, Thinking Mode=Thinking2026.0254.5969.6533.9848.932.55.5
Kimi K2System Category=Single Agent2026.0254.3665.0829.6741.351.123.5
MASBackbone=Doubao-Seed-1.6, Thinking Mode=Non-Thinking2026.0252.7565.1329.6542.652.124.5
OpenAI o3-highSystem Category=Single Agent2026.0252.6162.273444.074.59
SmolagentsBackbone=GPT-5-mini2026.0251.3157.6823.0430.5745
Gemini 2.5 ProSystem Category=Single Agent2026.0250.9863.623041.391.55
Doubao-Seed-1.6System Category=Single Agent, Thinking Mode=Non-Thinking2026.0248.9761.9827.2139.8613.5
Claude Sonnet 4System Category=End-to-End System, Thinking Mode=Thinking2026.0248.458.4724.1133.492.55
Doubao-Seed-1.6System Category=Single Agent, Thinking Mode=Thinking2026.0248.2763.8629.944.122.635
OpenAI o3System Category=End-to-End System2026.0245.5256.4923.9136.0335.5
MASBackbone=DeepSeek-R12026.0244.2860.3422.8736.590.753
DeepSeek-R1System Category=Single Agent2026.0241.2655.0920.6631.690.371.5