Skip to main content
Benchmark Registry
ModelsBenchmarksOrganizationsCompare

DeepSearchQA

Benchmark
DeepSearchQA
Evaluated by
Google DeepMind
Release date
December 11, 2025
Version
DeepSearchQA 900-prompt set
Metric
F1 score

Results

4 results

LatestHistory
All providersAnthropicMeta AI (originally Facebook AI Research)
DeepSearchQA 900-prompt set results
ProviderModelScoreSourceRegistry No.
Meta AI (originally Facebook AI Research)Muse Spark 1.2 (xhigh)85.9%Source for Muse Spark 1.2 (xhigh) on DeepSearchQA 900-prompt set (opens in a new tab)80003
Meta AI (originally Facebook AI Research)Muse Spark 1.3 (max)90.3%Source for Muse Spark 1.3 (max) on DeepSearchQA 900-prompt set (opens in a new tab)80005
Meta AI (originally Facebook AI Research)Muse Glimmer 30B (high)74.6%Source for Muse Glimmer 30B (high) on DeepSearchQA 900-prompt set (opens in a new tab)80004
Meta AI (originally Facebook AI Research)Muse Spark (thinking)74.8%Source for Muse Spark (thinking) on DeepSearchQA 900-prompt set (opens in a new tab)80001
Page 1 of 1

© 2026 Densa Labs

Toggle between the data update date and the application build time.
Legal
Color theme