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

5 results

LatestHistory
All providersAnthropicMeta AI (originally Facebook AI Research)
DeepSearchQA 900-prompt set results
ProviderModelScoreSourceRegistry No.
AnthropicClaude Opus 5 (medium)92.8%Source for Claude Opus 5 (medium) on DeepSearchQA 900-prompt set (opens in a new tab)20014
AnthropicClaude Opus 5 (max)95.0%Source for Claude Opus 5 (max) on DeepSearchQA 900-prompt set (opens in a new tab)20014
AnthropicClaude Opus 5 (high)94.1%Source for Claude Opus 5 (high) on DeepSearchQA 900-prompt set (opens in a new tab)20014
AnthropicClaude Opus 5 (low)91.0%Source for Claude Opus 5 (low) on DeepSearchQA 900-prompt set (opens in a new tab)20014
AnthropicClaude Opus 5 (xhigh)94.6%Source for Claude Opus 5 (xhigh) on DeepSearchQA 900-prompt set (opens in a new tab)20014
Page 1 of 1

© 2026 Densa Labs

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