AA-Briefcase analytical quality leaderboard
AA-Briefcase analytical quality
2 models tested · Updated 2026-07-21 · Verified sources only
GLM-5.2 leads at 1328.49Elo
1
GLM-5.2
Z AI · BenchmarkList/AA · 2026-07-21
Analytical rigor and evidential support. 667 Elo above Qwen 3.6 27B.
1328.49Elo
2
Qwen 3.6 27B
Alibaba · BenchmarkList/AA · 2026-07-21
Qwen's clearest professional-work weakness: 667 Elo below GLM on analytical rigor.
661.85Elo
benchmark.space canonical public ledger of AI capability