Ling 3.0 Flash VL Benchmarks, Specifications & Availability

Explore Ling 3.0 Flash VL from inclusionAI: published specifications, source-linked vendor benchmarks, independent evaluator coverage and recorded pricing when available.

Compare Ling 3.0 Flash VL with other models →Explore data coverage

Published specifications

Provider: inclusionAI
Access: Open weights
License: MIT
Context window: 256K
Total parameters: 124B
Active parameters: 5.5B
Released: 2026-09-10
Modalities: text, image, video
Family: Ling 3.0

Model card · Announcement · Website · OpenRouter

Model notes

124B MoE / ~5.5B active; native vision+video on Ling 3.0 Flash backbone. Free OR sibling inclusionai/ling-3.0-flash-vl:free exists — site uses paid slug for pricing. OR API lists 128K context; card advertises 256K (YaRN). Open weights verified on Hugging Face https://huggingface.co/inclusionAI/Ling-3.0-flash-VL (2026-09-25).

Pricing · OpenRouter

Dated cached OpenRouter rates in USD per 1M tokens. Open the dashboard for live enhancements. Per-metric endpoint minima can refer to different providers; they are not a guaranteed combined rate from one endpoint.

Recorded pricing tiers
Tier	Input / 1M	Output / 1M	Cached input / 1M	Cache write / 1M	Date & source
Default	[object Object]	[object Object]	[object Object]	—	2026-10-03 · OpenRouter source

Recorded pricing notes

Paid slug (not :free). No -contribute sibling on OR 2026-09-23.; min-healthy endpoint minima 2026-10-01; discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); min-healthy endpoint minima 2026-10-01; discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); min-healthy endpoint minima 2026-10-02; discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); min-healthy endpoint minima 2026-10-03; discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied); discount flag 0.72 on Novita (undocumented, not applied)

Official / vendor benchmarks

Default headline records. Own-vendor, peer-vendor and third-party provenance remain visible in evidence; configurations may differ.

Official / vendor headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
CountBench	97.3%unknown effort	All 1 recorded result & sources 97.3% · raw 97.33 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 Visual perception CountBench; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
WorldVQA	45.7%unknown effort	All 1 recorded result & sources 45.7% · raw 45.67 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 WorldVQA; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
MMMU Pro (no tools)	79%unknown effort	All 1 recorded result & sources 79% · raw 79 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 MMMU-Pro; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
MathVision	84.9%unknown effort	All 1 recorded result & sources 84.9% · raw 84.87 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 MathVision; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
Humanity's Last Exam (Multimodal)	19.9%unknown effort	All 1 recorded result & sources 19.9% · raw 19.88 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 Humanity's Last Exam-MM; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
OmniDocBench 1.5	91.4%unknown effort	All 1 recorded result & sources 91.4% · raw 91.35 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 OmniDocBench1.5; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
CharXiv RQ	81.3%unknown effort	All 1 recorded result & sources 81.3% · raw 81.3 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 CharXiv_RQ; from inclusionAI card chart (no Python tools) https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
MMSearch	79%unknown effort	All 1 recorded result & sources 79% · raw 79 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 MMSearch; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
ClawEval-MM	59.9%unknown effort	All 1 recorded result & sources 59.9% · raw 59.9 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 ClawEval-MM; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
WebVoyager	90.8%unknown effort	All 1 recorded result & sources 90.8% · raw 90.83 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 WebVoyager; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
Vision2Web	57.7%unknown effort	All 1 recorded result & sources 57.7% · raw 57.69 % Headline · unknown effort · Own vendor Source/record date: 2026-09-10 Vision2Web; from inclusionAI card chart https://huggingface.co/inclusionAI/Ling-3.0-flash-VL
AA Intelligence Index (vendor-cited)	42unknown effort	All 1 recorded result & sources 42 · raw 42 index Headline · unknown effort · Own vendor Source/record date: 2026-09-10 Vendor-reported AA Intelligence Index v4.1.1 (not live AA v4.3) https://huggingface.co/inclusionAI/Ling-3.0-flash-VL

Independent evaluators

Evaluator harnesses are distinct from vendor measurements. Missing coverage is not a failed test.

Independent evaluator headline scores; expand evidence for every record
Benchmark / evaluator	Headline score	Evidence
Intelligence Index · Artificial Analysis	25unknown effort	All 1 recorded result & sources 25 · raw 25 index Headline · unknown effort · Independent evaluator Source/record date: 2026-10-03 Current AA model leaderboard; https://artificialanalysis.ai/models/ling-3-0-flash-vl
Output speed · Artificial Analysis	144 tok/sunknown effort	All 1 recorded result & sources 144 tok/s · raw 144 tok/s Headline · unknown effort · Independent evaluator Source/record date: 2026-09-23 AA page: 144 tokens per second https://artificialanalysis.ai/models/ling-3-0-flash-vl
GDPval-AA Elo · Artificial Analysis	1150unknown effort	All 1 recorded result & sources 1150 · raw 1150 Elo Headline · unknown effort · Independent evaluator Source/record date: 2026-09-23 GDPval-AA v2.1 Elo; Ling-3.0-flash-VL https://artificialanalysis.ai/evaluations/gdpval-aa

Read how we select and source scores or the comparison guide.