AA-LCR leaderboard
AA-LCR
2 models tested · Updated 2026-07-21 · Verified sources only
GLM-5.2 leads at 71.3%
1
GLM-5.2
Z AI · Artificial Analysis · 2026-07-21
Long context reasoning. Small 2.6-point lead over Qwen suggests context isn't the differentiator.
71.3%
2
Qwen 3.6 27B
Alibaba · Artificial Analysis · 2026-07-21
Long context reasoning. Only 2.6 points behind GLM — reading context isn't Qwen's main limitation.
68.7%
benchmark.space canonical public ledger of AI capability