inclusionAI

Ling 3.0 Flash

Ling 3.0 Flash is an open-weight model from inclusionAI, released Jul 23, 2026. Its best result is #44 of 143 on LiveCodeBench with 83.99%. It costs $0.021 per million input tokens and $0.063 per million output tokens, with a 256K-token context window.

Developer
inclusionAI
Released
Jul 23, 2026
Context window
256K
Price in / out, per 1M tokens
$0.021 / $0.063
Weights
Open
Inputs
Text
Reasoning
Yes
Tool use
Yes
Hugging Face downloads, 30 days
9.7K
Hugging Face likes
436

Benchmarks

BenchmarkScore barAccuracyRankCost / test
SWE-benchCoding65.20%70 / 85$0.03
Vibe Code BenchCoding2.91%108 / 115$0.29
LiveCodeBenchCoding83.99%44 / 143$0.075 / $0.22
Legal Research BenchLaw0.00%85 / 85$0.04
MedCodeMedicine32.27%90 / 107$0.075 / $0.22
GPQA DiamondReasoning84.85%50 / 138$0.075 / $0.22
MMLU-ProReasoning82.01%82 / 138$0.075 / $0.22

Vals AI, as of Oct 24, 2026.

Compare Ling 3.0 Flash

Questions

Who makes Ling 3.0 Flash?

Ling 3.0 Flash is made by inclusionAI.

How much does Ling 3.0 Flash cost?

$0.021 per million input tokens and $0.063 per million output tokens, at its provider’s list price.

What is Ling 3.0 Flash’s context window?

256K tokens (262,144).

Is Ling 3.0 Flash open source?

Ling 3.0 Flash has open weights, downloadable from Hugging Face (inclusionAI/Ling-3.0-flash).

Sources

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.