InclusionAI

Ling 3.0 Flash

Aug 4, 2026ReasoningOpen weightsModels.devHugging Face

Compare

Intelligence

20.1

#259 of 768Rank 259 of 768 measured models

Coding

50.6

#122 of 299Rank 122 of 299 measured models

Output speed

321 t/s

#14 of 425Rank 14 of 425 measured models

Price/1M

$0.111

#116 of 726Rank 116 of 726 measured models

Context window

1M

#90 of 1296Rank 90 of 1296 measured models

Cost per task

$0.0277

#22 of 218Rank 22 of 218 measured models

Ling 3.0 Flash scores 20.1 on the Artificial Analysis Intelligence Index, ranking 259th of 768 measured models. The closest models on this index are GPT-5.1 Codex mini (High) (20.4), o3 (20.2), and Qwen3.8 27B (20.1). At $0.111 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.1 Codex mini (High) ($0.688), o3 ($3.50), and Qwen3.8 27B ($1.13). With an output speed of 321 t/s, it is faster than GPT-5.1 Codex mini (High) (175 t/s), o3 (151 t/s), and Qwen3.8 27B (41.4 t/s).