Language modelActive

Qwen 3 Next 80B A3B Thinking

Alibaba

Released: September 9, 2025
Data date: September 8, 2026

Speed: 194.1 tokens/s
Output throughput
Price: $0.15 · $1.2
Input · Output / 1M tokens
Input: Text
Output: Text

Qwen 3 Next 80B A3B Thinking is the reasoning configuration of the open 80B-A3B MoE model. Only 3 billion of its 80 billion parameters are active per token. The checkpoint supports Thinking and tool calls. With 262,144 native context tokens and extension to 1,010,000, it fits long tasks that benefit from additional internal reasoning.

For direct responses without visible reasoning, use Qwen 3 Next 80B A3B Instruct. The two variants share the MoE foundation but not automatically their behavior or response format. This repository uses Apache-2.0 and remains an open-weight model.

Profile

Specifications and access

Published information about this model. Existing estimates are explicitly labeled.

Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	80BSource
Active parameters	3BSource
Context window	262,144 tokensSource
Weights repository	Qwen/Qwen3-Next-80B-A3B-ThinkingSource
License	Apache-2.0Source
Architecture	Qwen3 causal language model with sparse MoE and 8 activated expertsSource
Input	TextSource
Output	TextSource
Reasoning mode	thinking modeSource
Tool calling	YesSource
Structured output	YesSource
Native context window	262,144 tokensSource
Maximum context window	1,010,000 tokensSource
Parameters	80 BSource
Active parameters	3 BSource
Languages	119 languages and dialectsSource
Repository created	2025-09-09 (Repository creation date is a precise publication proxy, but may differ from the public announcement date or an individual checkpoint's first availability.)Source
Training tokens	36 trillionSource

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMLU-Pro (Show measurement, test conditions, and source)

Source value: 82.7
Score: 82.7
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:0
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

MMLU-Redux (Show measurement, test conditions, and source)

Source value: 92.5
Score: 92.5
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:1
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

GPQA (Show measurement, test conditions, and source)

Source value: 77.2
Score: 77.2
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:2
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

SuperGPQA (Show measurement, test conditions, and source)

Source value: 60.8
Score: 60.8
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:3
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

AIME25 (Show measurement, test conditions, and source)

Source value: 87.8
Score: 87.8
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:4
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

HMMT25 (Show measurement, test conditions, and source)

Source value: 73.9
Score: 73.9
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:5
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

LiveBench 241125 (Show measurement, test conditions, and source)

Source value: 76.6
Score: 76.6
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:6
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

LiveCodeBench v6 (25.02-25.05) (Show measurement, test conditions, and source)

Source value: 68.7
Score: 68.7
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:7
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

OJBench (Show measurement, test conditions, and source)

Source value: 29.7
Score: 29.7
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:9
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

IFEval (Show measurement, test conditions, and source)

Source value: 88.9
Score: 88.9
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:10
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

Arena-Hard v2 (Show measurement, test conditions, and source)

Source value: 62.3
Score: 62.3
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:11
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

WritingBench (Show measurement, test conditions, and source)

Source value: 84.6
Score: 84.6
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:qwen-3-next-80b-a3b-thinking:12
Source type: vendor-reported
Evaluator: Qwen official Hugging Face model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Official model-card table; shots/tools/decoding not stated in the card row

Source Qwen official Hugging Face model card

Page 1 of 3

Evidence

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Type	Evidence and data date
Speed	Alibaba, Reasoning. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-Next 80B A3B Thinking model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-Next 80B A3B Thinking model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Additional source	Model metadata (retrieved September 8, 2026) · Qwen3 Technical Report · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

Qwen 3 Next 80B A3B Thinking

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Sources and data date