HN Showcase
Back to browse
Apodex-1.0-H – Beats Claude-Opus-4.7 on deep research (90.3 BrowseComp)

Apodex-1.0-H – Beats Claude-Opus-4.7 on deep research (90.3 BrowseComp)

by wuqiaocauc·Jun 10, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidBig Brain

Step-level verification before moving forward is a genuinely interesting architectural choice.

Strengths
  • •Verifies each conclusion before proceeding to next reasoning step
  • •Branch off any report and search across all threads
  • •Claims 90.3% on BrowseComp benchmark against Claude-Opus
Weaknesses
  • •Deep research AI space is extremely crowded with Perplexity, Consensus, Elicit
  • •Benchmark claims are unverifiable from the landing page alone
Category
AI/ML
Target Audience

Researchers, analysts, knowledge workers

Similar To

Perplexity · Consensus · Elicit

Similar Projects