Ling-3.0-flash-Fin full benchmark results: ~67k output tokens per task

ArtificialAnlys · x · 2026-09-16

Artificial Analysis published full results for Ant Group's Ling-3.0-flash-Fin across all 10 evaluations in the Intelligence Index v4.3. A notable finding: the model is verbose, averaging 67k output tokens per task — 34% more than Ling-3.0-flash-VL (50k) and over 3x MiniMax-M2.7 (21k).

Related event: Ant's Open-Source Ling-3.0-flash-Fin Benchmarked by Artificial Analysis(3 posts)→

Original post →

More from Models

Models channel →