Model profile / Alibaba Cloud

Qwen3.8-Flash-Next

Qwen's experimental open-weight multimodal MoE preview of the Qwen4 architecture, with 125B total parameters, 6B activated parameters, 51B n-gram embeddings and native 262,144-token context.

26 Aug 2026Open weightsProvider

Sources & details

Four areas of evidence

The capabilities behind the model.

How the indices work

Reasoning

113.7Index points

Mathematical and scientific problem solving.

This model│ Other models · 155 rated

Score and research range

Full-precision point: 113.656986542971
Range: 111.04–116.28 · 90% Research Range
Scope: Conditional fuller R0 A

Score includes qualified prediction of missing evidence.

Coding

106.3Index points

Software engineering and programming.

This model│ Other models · 39 rated

Score and research range

Full-precision point: 106.33956200619036
Range: No qualified range available
Scope: Frozen Coding score under admitted comparison/reference/source reweighting

Score uses the admitted direct native evidence under the selected method.

General

49.0Index points

Factual reliability and instruction following.

This model│ Other models · 61 rated

Score and research range

Full-precision point: 49.019500000000015
Range: No qualified range available
Scope: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U

Score uses the admitted direct native evidence under the selected method.

Agentic

No current rating

Tool use, workflows and professional tasks.

Awaiting a qualified category score

18retained native records

12evidence families

Capabilities estimateQualified original evidence across four areas.

Current index snapshot · 2026-09-16. Each category uses its own scale; scores across categories are not directly comparable. Evidence counts describe the retained Capabilities inputs; a family can contain several tasks or configurations. A point lead does not establish superiority.

Performance in context

Capabilities, price & speed.

Explore every model

Qwen3.8-Flash-Next is highlighted wherever a compatible measurement is available.

Qwen3.8-Flash-Next: Regional/tier or mutable endpoint-to-checkpoint binding unresolved; no price inherited

Lumina Capabilities Index

Capabilities versus API price

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 62 models · 1 highlighted

Chart loads as you explore

Qwen3.8-Flash-Next: No exact base-profile release and documented 10K output measurement; other effort/protocol/alias records not substituted

Lumina Capabilities Index

Capabilities versus output speed

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 72 models · Developer API · 10K · 1 highlighted

Chart loads as you explore

Explore the detail

Sources & model details.

Original evidence, with its context.

Current index evidence 4Scores, research ranges and the sources behind each category.

Capabilities

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: C1 native factor under conditional crossed source/family reweighting of admitted fixed-corpus reference and own portfolio
Sources: Artificial Analysis:Artificial Analysis · LiveBench:LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Coding

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Frozen Coding score under admitted comparison/reference/source reweighting
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Reasoning

Score includes qualified prediction of missing evidence.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Conditional fuller R0 A
Sources: aa
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

General

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Benchmark measurements 25Published values in each benchmark’s own units.

25 measurements

Qwen3.8-Flash-Next published benchmark measurements
Benchmark	Result	Published configuration	Source
AA Long Context Reasoningstandard	77%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis AA-LCR evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
CritPtstandard	11.143%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis CritPt evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
GDPval-AA v2v2	62.139%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis GDPval-AA v2	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
GPQA Diamonddiamond	92.323%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis GPQA Diamond evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Humanity's Last Examtext-only current	38.044%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis text-only HLE evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
SciCode2024	46.875%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis SciCode evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
τ³-Banking3	45.361%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis tau3-Banking evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Terminal-Bench2.1	86.142%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis Terminal-Bench v2.1 in e2b	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Agents Last ExamPass@1	24.3%	Qwen3.8-Flash-Next (xhigh default thinking configuration)system:qwen3-8-flash-next:ale-pass1	Qwen3.8-Flash-Next current official launch page ↗Observed 2026-08-26 · checked 2026-08-29source-checked · reference-only
Agents Last ExamScore	51.2%	Qwen3.8-Flash-Next (xhigh default thinking configuration)system:qwen3-8-flash-next:ale-score	Qwen3.8-Flash-Next current official launch page ↗Observed 2026-08-26 · checked 2026-08-29source-checked · reference-only

Showing 10 of 25 measurements

Specifications & source recordsDocumented model details and original references.

Model ID / checkpoint: Qwen/Qwen3.8-Flash-Next
Weight access: Open weights
Context window: 262,144
Maximum output: Not documented
Modalities: text, image, video
Details checked: 29 Aug 2026

Qwen3.8-Flash-Next current official launch pageQwen · Published 26 Aug 2026 · checked 27 Aug 2026 · source-checked Qwen3.8-Flash-Next launch and official provider evaluationsQwen · Published 26 Aug 2026 · checked 26 Aug 2026 · source-checked Qwen3.8-Flash-Next official model card and weightsQwen · Published 24 Aug 2026 · checked 26 Aug 2026 · source-checked Qwen3.8-Flash-Next official ModelScope weightsQwen · Published 26 Aug 2026 · checked 26 Aug 2026 · source-checked Qwen3.8-Flash-Next official repository and technical reportQwen · Published 24 Aug 2026 · checked 26 Aug 2026 · source-checked Qwen3.8-Flash-Next individual evaluationsArtificial Analysis · Published 26 Aug 2026 · checked 29 Aug 2026 · source-checked

Specialist task evidenceSeparate agent runs and execution conditions.

No specialist task observations retained for this model.

All models

Model profile / Alibaba Cloud

Qwen3.8-Flash-Next

Qwen's experimental open-weight multimodal MoE preview of the Qwen4 architecture, with 125B total parameters, 6B activated parameters, 51B n-gram embeddings and native 262,144-token context.

26 Aug 2026Open weightsProvider

Sources & details

Four areas of evidence

The capabilities behind the model.

How the indices work

Reasoning

113.7Index points

Mathematical and scientific problem solving.

This model│ Other models · 155 rated

Score and research range

Full-precision point: 113.656986542971
Range: 111.04–116.28 · 90% Research Range
Scope: Conditional fuller R0 A

Score includes qualified prediction of missing evidence.

Coding

106.3Index points

Software engineering and programming.

This model│ Other models · 39 rated

Score and research range

Full-precision point: 106.33956200619036
Range: No qualified range available
Scope: Frozen Coding score under admitted comparison/reference/source reweighting

Score uses the admitted direct native evidence under the selected method.

General

49.0Index points

Factual reliability and instruction following.

This model│ Other models · 61 rated

Score and research range

Full-precision point: 49.019500000000015
Range: No qualified range available
Scope: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U

Score uses the admitted direct native evidence under the selected method.

Agentic

No current rating

Tool use, workflows and professional tasks.

Awaiting a qualified category score

18retained native records

12evidence families

Capabilities estimateQualified original evidence across four areas.

Performance in context

Capabilities, price & speed.

Explore every model

Qwen3.8-Flash-Next is highlighted wherever a compatible measurement is available.

Qwen3.8-Flash-Next: Regional/tier or mutable endpoint-to-checkpoint binding unresolved; no price inherited

Lumina Capabilities Index

Capabilities versus API price

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 62 models · 1 highlighted

Chart loads as you explore

Qwen3.8-Flash-Next: No exact base-profile release and documented 10K output measurement; other effort/protocol/alias records not substituted

Lumina Capabilities Index

Capabilities versus output speed

The current Capabilities cohort, with this model highlighted.

Lumina

2025+ · 72 models · Developer API · 10K · 1 highlighted

Chart loads as you explore

Explore the detail

Sources & model details.

Original evidence, with its context.

Current index evidence 4Scores, research ranges and the sources behind each category.

Capabilities

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: C1 native factor under conditional crossed source/family reweighting of admitted fixed-corpus reference and own portfolio
Sources: Artificial Analysis:Artificial Analysis · LiveBench:LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Coding

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Frozen Coding score under admitted comparison/reference/source reweighting
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Reasoning

Score includes qualified prediction of missing evidence.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: Conditional fuller R0 A
Sources: aa
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

General

Score uses the admitted direct native evidence under the selected method.

Exact checkpoint: qwen-3-8-flash-next
Method: methods-a4471cee84fd478d2ed3
Range interpretation: General G4 under admitted instruction-task portfolio resampling conditional on exact recorded R and U
Sources: Artificial Analysis · LiveBench
Source cutoff: {"asOfMeaning":"Selected local candidate: retained historical measurements plus reviewed additions; execution dates remain source-native.","newIdentityRecovery":"2026-09-13T08:41:08.804270+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Inherited pinned baseline source vintages plus retained4A/4A.1 originals and SWE owner correction; heterogeneous execution dates, often unknown. Not a claim of simultaneous2026-09-13 execution."}

Explore this index

Benchmark measurements 25Published values in each benchmark’s own units.

25 measurements

Qwen3.8-Flash-Next published benchmark measurements
Benchmark	Result	Published configuration	Source
AA Long Context Reasoningstandard	77%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis AA-LCR evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
CritPtstandard	11.143%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis CritPt evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
GDPval-AA v2v2	62.139%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis GDPval-AA v2	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
GPQA Diamonddiamond	92.323%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis GPQA Diamond evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Humanity's Last Examtext-only current	38.044%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis text-only HLE evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
SciCode2024	46.875%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis SciCode evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
τ³-Banking3	45.361%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis tau3-Banking evaluation	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Terminal-Bench2.1	86.142%	Qwen3.8-Flash-Next (Artificial Analysis independent run)Artificial Analysis Terminal-Bench v2.1 in e2b	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29independently-verified · reference-only
Agents Last ExamPass@1	24.3%	Qwen3.8-Flash-Next (xhigh default thinking configuration)system:qwen3-8-flash-next:ale-pass1	Qwen3.8-Flash-Next current official launch page ↗Observed 2026-08-26 · checked 2026-08-29source-checked · reference-only
Agents Last ExamScore	51.2%	Qwen3.8-Flash-Next (xhigh default thinking configuration)system:qwen3-8-flash-next:ale-score	Qwen3.8-Flash-Next current official launch page ↗Observed 2026-08-26 · checked 2026-08-29source-checked · reference-only

Showing 10 of 25 measurements

Specifications & source recordsDocumented model details and original references.

Model ID / checkpoint: Qwen/Qwen3.8-Flash-Next
Weight access: Open weights
Context window: 262,144
Maximum output: Not documented
Modalities: text, image, video
Details checked: 29 Aug 2026

Specialist task evidenceSeparate agent runs and execution conditions.

No specialist task observations retained for this model.

The capabilities behind the model.

Capabilities, price & speed.

Capabilities versus API price

Capabilities versus output speed

Sources & model details.

Capabilities

Coding

Reasoning

General

More from Alibaba Cloud.

Qwen3.8-27B

Qwen3.6 Plus

Qwen3.5-122B-A10B

The capabilities behind the model.

Capabilities, price & speed.

Capabilities versus API price

Capabilities versus output speed

Sources & model details.

Capabilities

Coding

Reasoning

General

More from Alibaba Cloud.

Qwen3.8-27B

Qwen3.6 Plus

Qwen3.5-122B-A10B