AlibabaLanguage model
Qwen 3.8 Flash Next
Qwen 3.8 Flash Next has no overall index value yet because there are too few independent benchmark results.
Intelligencenot ranked yet
n/aOverall indexhigher is better
SpeedRank 71 of 101
64Tokens per secondhigher is better
Priceno API price
n/aper 1M tokenslower is better
ContextRank 67 of 103
262Ktokens at once≈ 390 A4 pages
PopularityRank 25 of 785
61out of 100same as last month
based on search, usage and attention
Summary
At 64 tokens per second it writes slower than a typical model (87).
Qwen 3.8 Flash Next is an open experimental architecture checkpoint, not simply a smaller Qwen3.8 model. Qwen replaces Gated Attention with Qwen Sparse Attention and combines it with Gated DeltaNet. The model has 125 billion parameters, activates 6 billion, and adds 51 billion n-gram embeddings. It accepts text, images, and video and uses Thinking mode by default.
Native context reaches 262,144 tokens and can be extended to 1 million. Thinking can be disabled through the API. The official serving model Qwen 3.8 Flash is based on this Next checkpoint according to its model card and adds 1M context plus built-in tools by default.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 97 published benchmark results
Page 1 of 9
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.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 11.1428571428571
- Score
- 11.1428571428571
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled. Score display: 11.1%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled
- Context
- This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
MMMU-Pro: Overall (Show measurement, test conditions, and source)
- Source value
- 79.7687861271676
- Score
- 79.7687861271676
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- AA cohort: 1,730 questions
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Score display: 79.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled
- Context
- The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.. This result is retained as historical evidence and is not interchangeable with current results.
MMMU-Pro: Overall (Show measurement, test conditions, and source)
- Source value
- 79.7687861271676
- Score
- 79.7687861271676
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- AA cohort: 1,730 questions
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Score display: 79.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled
- Context
- The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
- Source value
- 23.533333333333335
- Score
- 23.533333333333335
- Metric
- AA-Omniscience Accuracy
- Unit
- %
- Benchmark version
- AA Omniscience diagnostic
- Category
- knowledge
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 23.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
- Context
- This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.. This result is retained as historical evidence and is not interchangeable with current results.
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
- Source value
- 23.533333333333335
- Score
- 23.533333333333335
- Metric
- AA-Omniscience Accuracy
- Unit
- %
- Benchmark version
- AA Omniscience diagnostic
- Category
- knowledge
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 23.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
- Context
- This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
- Source value
- 46.774193548387096
- Score
- 46.774193548387096
- Metric
- AA-Omniscience Hallucination Rate
- Unit
- %
- Benchmark version
- AA Omniscience diagnostic
- Category
- knowledge
- Task
- overall
- Task label
- Overall
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 46.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
- Context
- This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.. This result is retained as historical evidence and is not interchangeable with current results.
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
- Source value
- 46.774193548387096
- Score
- 46.774193548387096
- Metric
- AA-Omniscience Hallucination Rate
- Unit
- %
- Benchmark version
- AA Omniscience diagnostic
- Category
- knowledge
- Task
- overall
- Task label
- Overall
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Source model ID: artificial-analysis/9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae/qwen3-8-flash-next/qwen3-8-flash-next. Source model name: Qwen 3.8 Flash Next. Provider reported by source: Alibaba. Model snapshot: Qwen3.8-Flash-Next. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 46.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Qwen3.8-Flash-Next (release qwen3-8-flash-next, row qwen3-8-flash-next, UUID 9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
- Context
- This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.
ExtractBench mean (Show measurement, test conditions, and source)
- Source value
- 89.88
- Score
- 89.88
- Metric
- ExtractBench unified value F1, unweighted document mean across 370 documents
- Unit
- %
- Benchmark version
- v1.0
- Category
- information extraction
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- LlamaIndex / Run-Llama ExtractBench
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Qwen3.8-Flash-Next; ExtractBench v1.0; task date 2026-08-29; qwen3_8_flash_next_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint Qwen/Qwen3.8-Flash-Next-FP8; one-shot unified value F1 on the publisher's 0-100 scale.
- Context
- The current publisher dataset is v1.1, but this run predates the 2026-09-29 changes and remains labelled v1.0.
ExtractBench short (Show measurement, test conditions, and source)
- Source value
- 94.82
- Score
- 94.82
- Metric
- ExtractBench unified value F1, short-document split
- Unit
- %
- Benchmark version
- v1.0
- Category
- information extraction
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- LlamaIndex / Run-Llama ExtractBench
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Qwen3.8-Flash-Next; ExtractBench v1.0; task date 2026-08-29; qwen3_8_flash_next_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint Qwen/Qwen3.8-Flash-Next-FP8; one-shot unified value F1 on the publisher's 0-100 scale.
- Context
- The current publisher dataset is v1.1, but this run predates the 2026-09-29 changes and remains labelled v1.0.
ExtractBench medium (Show measurement, test conditions, and source)
- Source value
- 87.81
- Score
- 87.81
- Metric
- ExtractBench unified value F1, medium-document split
- Unit
- %
- Benchmark version
- v1.0
- Category
- information extraction
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- LlamaIndex / Run-Llama ExtractBench
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Qwen3.8-Flash-Next; ExtractBench v1.0; task date 2026-08-29; qwen3_8_flash_next_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint Qwen/Qwen3.8-Flash-Next-FP8; one-shot unified value F1 on the publisher's 0-100 scale.
- Context
- The current publisher dataset is v1.1, but this run predates the 2026-09-29 changes and remains labelled v1.0.
ExtractBench long (Show measurement, test conditions, and source)
- Source value
- 37.74
- Score
- 37.74
- Metric
- ExtractBench unified value F1, long-document split
- Unit
- %
- Benchmark version
- v1.0
- Category
- information extraction
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- LlamaIndex / Run-Llama ExtractBench
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Qwen3.8-Flash-Next; ExtractBench v1.0; task date 2026-08-29; qwen3_8_flash_next_fp8_vllm_extract_oneshot_structured_output_file; served checkpoint Qwen/Qwen3.8-Flash-Next-FP8; one-shot unified value F1 on the publisher's 0-100 scale.
- Context
- The current publisher dataset is v1.1, but this run predates the 2026-09-29 changes and remains labelled v1.0.
ClawEval-MM (Show measurement, test conditions, and source)
- Source value
- 64.4
- Score
- 64.4
- Metric
- Pass@3
- Unit
- %
- Category
- Multimodal tool use
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Qwen/Qwen3.8-Flash-Next model card at revision de4b8e4d43b917e7706784d8bb445c9af86a3540
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact model-card table column Qwen3.8-Flash-Next, for the open-weight checkpoint. The card does not identify an immutable evaluation-weight revision. The card defines Pass@3 as the percentage passing at least one of three trials.
- Context
- The model card does not publish sample counts or a benchmark version and does not bind these table results to an immutable weight revision. Do not transfer them to the separately hosted Qwen3.8-Flash API, which the card says adds production features.
Page 1 of 9
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 100 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 7, 2026
Qwen 3.8 Flash NextQwen 3.8 Flash 62Gemini 3.8 Flash 61Muse Spark 1.3 61GPT-6 Luna 60
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Qwen 3.8 Flash Next, chosen by model line, developer, size, price and release date.
- Qwen 3.5 122B A10BAlibaba · same developer
- Qwen 3.8 FlashAlibaba · same developer
- Qwen 3.8 27BAlibaba · same developer
- Qwen 3.6 35B A3BAlibaba · same developer
- Qwen 3.6 27BAlibaba · same developer
- Qwen 3.8 2.4T A95BAlibaba · same developer
- Qwen3.5 4BAlibaba · same developer
- Qwen 3.8 Max 0902Alibaba · same developer
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Qwen 3.8 Flash Next
How large is the context window of Qwen 3.8 Flash Next?
262,144 tokens. That is how much text Qwen 3.8 Flash Next reads at once, about 390 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Qwen 3.8 Flash NextRank 67 of 103262K
Kimi K2.6262K
Qwen 3.8 27B262K
Kimi K2.7 Code262K
Kimi K2.5262K
Nemotron 3 Ultra262K
Kimi K2 Thinking262K
How fast is Qwen 3.8 Flash Next?
64 tokens per second. That is slower than a typical model at 87.
Measured by Artificial Analysis on Nov 6, 2026. AA 3.0.0, including time to first token, averaged across available workloads and five days.
Claude Opus 566
Qwen 3.8 Flash NextRank 71 of 10164
Claude Opus 4.564
GPT-5.464
GLM-5.363
GLM-562
Claude Sonnet 4.660
Can I run Qwen 3.8 Flash Next locally?
Yes, the weights are open. With 125B parameters it needs a lot of memory, more a server than a laptop.
Stated by Alibaba
- Open weights
- yes
- License
- Qwen Community License 1.0
- Parameters
- 125B
- active per token
- 6B
Sources and data date
Show all 27 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 3 | 0 | 4 |
| LiveBench | 0 | 0 | 38 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 38 measurements are not yet assigned to a test series.
| Type | Evidence and data date |
|---|---|
| Speed | Alibaba, Reasoning enabled; effort unspecified. AA 3.0.0, including time to first token, averaged across available workloads and five days. Retrieved November 6, 2026. |
| Input | Documented modalities. Retrieved October 27, 2026. |
| Output | Documented modalities. Retrieved October 27, 2026. |
| Research status | Research date October 15, 2026. 13 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | reasoning effort and pass@k Note The cited result does not report reasoning effort or pass@k; exact task date and serving/checkpoint details are recorded in the benchmark configuration. |
| Unresolved | benchmark unit or scale Original wording Tables call the values scores but do not state a measurement unit or score scale; unit remains unknown. |
| Not published | evaluated sample count Original wording No evaluated N is stated for these Table 2-3 results. |
| Not published | confidence interval Original wording No confidence interval is stated for these Table 2-3 results. |
| Unresolved | exact checkpoint and serving route Original wording The paper names Qwen3.8-Flash-Next with QSA but does not pin an immutable checkpoint revision or hosted serving route. It separately identifies Base variants in Table 11. |
| Unresolved | long-context evaluation protocol versus model-card context Original wording Table 3 reports sequence lengths through 1M tokens, while the pinned model profile lists 262144 context; the source does not reconcile this difference. |
| Additional source | Hugging Face · Qwen3.8-Flash-Next model card · Editorial description reviewed October 2, 2026 |
| Additional source | Artificial Analysis (retrieved November 2, 2026) |
| Additional source | Artificial Analysis (retrieved October 29, 2026; November 2, 2026; November 7, 2026) |
| Additional source | Artificial Analysis (retrieved November 2, 2026; November 7, 2026)12 |
| Additional source | LlamaIndex / Run-Llama ExtractBench (retrieved October 15, 2026) |
| Additional source | LiveBench (retrieved October 16, 2026)1 (unavailable on November 2, 2026) https://livebench.ai/table_2026_09_02.csv2 (unavailable on November 2, 2026) https://livebench.ai/breakdown_2026_09_02.json |
| Additional source | Qwen/Qwen3.8-Flash-Next model card at revision de4b8e4d43b917e7706784d8bb445c9af86a3540 (retrieved October 17, 2026) |
| Additional source | Qwen Team, On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability (retrieved October 18, 2026) |
| Additional source | Model metadata (retrieved October 15, 2026)12 |
| Additional source | Model metadata (retrieved October 16, 2026)12 (unavailable on November 2, 2026) https://livebench.ai/categories_2026_09_02.json3 (unavailable on November 2, 2026) https://livebench.ai/notes_2026_09_02.json4 (unavailable on November 2, 2026) https://livebench.ai/static/js/main.d1b91202.js |
| Additional source | Model metadata (retrieved October 17, 2026) |
| Additional source | Qwen3.8 Flash Next announcement · Editorial description reviewed October 2, 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 | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |