Inference

WideResearch

A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces.

  • In index
  • Agentic
ModelsModels with a result.15
Top resultBest result on this test.83.9%Hy4 preview
Top-3 spreadPoints from first to third.2.0 pts
YearYear of release.N/A

Result and price

020406080100$0.03$0.1$0.3$1$3$10$30RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

15 results
#ModelResultThe score from the source.
01Hy4 preview83.9%
02Qwen3.8 Max81.9%
02Atria Dawn Preview81.9%
04Kimi K2.680.8%
04Ornith-1.5-397B80.8%
06dots3-note Preview78.9%
07Claude Opus 4.576.4%
08Qwen3.6 Plus74.3%
09Qwen3.5 397B74.0%
10Ling 3.0 Flash73.6%
11Kimi K2.572.7%
12GLM-569.8%
13Ornith-1.5-35B-A3B67.8%
14Qwen3.6-35B-A3B60.1%
15Ornith-1.5-9B59.5%