Inference

DeepSearchQA

An agentic browsing benchmark where models search the web, gather evidence, and answer list-style questions using browser tools.

  • In index
  • Agentic
ModelsModels with a result.18
Top resultBest result on this test.96.0%Atria Dawn Preview
Top-3 spreadPoints from first to third.1.0 pts
YearYear of release.N/A

Result and price

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

Results

18 results
#ModelResultThe score from the source.
01Atria Dawn Preview96.0%
02Claude Opus 595.0%
02Kimi K395.0%
04Claude Opus 4.893.1%
05Step 3.7 Flash92.8%
06Kimi K2.692.5%
07Apodex 1.192.4%
08dots3-note Preview92.1%
09Muse Spark 1.389.4%
10Muse Spark 1.184.9%
11Kimi K2.577.1%
12Muse Spark74.8%
13Muse Glimmer 30B74.6%
14Claude Opus 4.673.7%
15GPT-5.473.6%
16Gemini 3.1 Pro69.7%
17Grok 4.2062.8%
18Mercury 2.534.0%