Ling 3.0 Flash is Ant Group's Bailing team's new-generation native hybrid-reasoning model. It uses a Mixture-of-Experts architecture with 124B total parameters and 5.1B active, and is offered through API access and private deployment.
Parameters
124B (5.1B active)
Context Window
TBA
License
Proprietary (API)
Release Date
2026-08-07
Benchmark Performance
AA Intelligence Index
—
LMArena Elo
—
HLE
—
ARC-AGI-2
—
SWE-bench Verified
—
GPQA Diamond
—
MMLU-Pro
—
LiveCodeBench
—
AIME 2025
—
MATH-500
—
API Pricing
API pricing for this model is not yet available