inclusionAILanguage modelActive
Ling 3.1 Flash 1019
Ling 3.1 Flash 1019 has no overall index value yet because there are too few independent benchmark results.
Summary
Ling 3.1 Flash 1019 is inclusionAI's upgraded checkpoint in the Ling 3.1 Flash series. It is kept separate from the existing Ling 3.1 Flash profile and from the base checkpoint. The model card lists 560 billion total parameters, 25 billion active parameters per token, and a hybrid MoE architecture.
The model card reports five current vendor results. It lists 44 points on the Artificial Analysis Intelligence Index v4.3.2, about 1,524 Elo on AA-Briefcase, 68% on AutomationBench-AA, 26% on CritPt, and 57% on SciCode. These are inclusionAI claims. The card provides no sample counts, confidence intervals, or complete evaluation configurations.
The context window has an unresolved source conflict. The model card claims 1 million tokens, while config.json sets max_position_embeddings to 262,144 and explicitly sets rope_scaling to null. No single context limit is therefore marked as confirmed here.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 23 published benchmark results
Page 1 of 2
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.
AutomationBench-AA: Overall (Show measurement, test conditions, and source)
- Source value
- 67.54660741517775
- Score
- 67.54660741517775
- Metric
- Objectives completed without guardrail violations
- Unit
- %
- Benchmark version
- AA private 657-task split of AutomationBench v1.0.6
- Category
- agentic
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 67.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-automationbench-aa:AA private 657-task split of AutomationBench v1.0.6:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
CritPt v2 (Hard Subset): Overall (Show measurement, test conditions, and source)
- Source value
- 37.5
- Score
- 37.5
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2 hard subset
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 37.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-critpt-v2-hard-subset:v2 hard subset:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
- Context
- This is the 40-question hard subset of CritPt v2, not the full 70-question CritPt v2 run.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 26
- Score
- 26
- 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
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. 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: 26.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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
FrontierCode: Overall (Show measurement, test conditions, and source)
- Source value
- 17.0090151515151
- Score
- 17.0090151515151
- Metric
- Mean score over three attempts per task
- Unit
- %
- Benchmark version
- 2.0
- Category
- coding
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 17.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-frontiercode-2-0:2.0:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
GDP.pdf: Overall (Show measurement, test conditions, and source)
- Source value
- 12.6
- Score
- 12.6
- Metric
- All-pass rate
- Unit
- %
- Benchmark version
- unspecified
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 12.6%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-gdp-pdf:unspecified:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
HLE-Diamond: Overall (Show measurement, test conditions, and source)
- Source value
- 17.2
- Score
- 17.2
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- Diamond
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 17.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-hle-diamond:Diamond:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
- Source value
- 26.53333333333333
- Score
- 26.53333333333333
- 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
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. 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: 26.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
- Source value
- 36.29764065335753
- Score
- 36.29764065335753
- 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
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. 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: 36.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.
Terminal-Bench: Overall (Show measurement, test conditions, and source)
- Source value
- 32.8282828282828
- Score
- 32.8282828282828
- Metric
- Task success
- Unit
- %
- Benchmark version
- 4.0
- Category
- coding
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 32.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-terminal-bench-4:4.0:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
Terminal-Bench-Science: Overall (Show measurement, test conditions, and source)
- Source value
- 4.28571428571429
- Score
- 4.28571428571429
- Metric
- pass@1 task success rate
- Unit
- %
- Benchmark version
- 0.1.0
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Source model ID: artificial-analysis/539ed227-38f4-4bea-a015-117057c14b18/ling-3-1-flash-rc5/ling-3-1-flash-1019. Source model name: Ling 3.1 Flash 1019. Provider reported by source: InclusionAI. Model snapshot: Ling 3.1 Flash 1019. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 4.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-29-5a1b1cf41cd1. Source payload hash: 5a1b1cf41cd14d4fa7e1b5c737732505ff7f014395c8a19ff9385c13df09b106. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-10-29. Source cohort: artificial-analysis-terminal-bench-science:0.1.0:v5.0:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Ling 3.1 Flash 1019 (release ling-3-1-flash-rc5, row ling-3-1-flash-1019, UUID 539ed227-38f4-4bea-a015-117057c14b18, 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.. Reasoning: reasoning enabled
AutomationBench-AA (Show measurement, test conditions, and source)
- Source value
- 68
- Score
- 68
- Metric
- Percentage
- Unit
- %
- Category
- Agentic evaluation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inclusionAI Ling-3.1-flash-1019 model card
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Vendor-reported result. The card reports 68%. It does not provide benchmark run settings, sample count, or confidence interval.
- Context
- Vendor-quoted result; the card gives 62% for the preceding Ling-3.1-flash checkpoint.
CritPt (Show measurement, test conditions, and source)
- Source value
- 26
- Score
- 26
- Metric
- Percentage
- Unit
- %
- Category
- Scientific reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inclusionAI Ling-3.1-flash-1019 model card
- Status
- active
- Retrieved at
- 2026-10-29
- Methodology
- Vendor-reported result. The card reports 26%. It does not provide benchmark run settings, sample count, or confidence interval.
- Context
- Vendor-quoted result; the card gives 18% for the preceding Ling-3.1-flash checkpoint.
Page 1 of 2
All specifications
Architecture
- Architecture
- Hybrid-linear MoE with 63 KDA and 9 Gated MLA layers, 512 routed experts, one shared expert, and eight active experts per token.
- Source: Architecture
- Architecture
- Hybrid-linear MoE with 63 KDA and 9 Gated MLA layers, 512 routed experts, one shared expert, and eight active experts per token
- Source: Architecture
Licence and access
Further details
- Model variant
- The model card describes Ling-3.1-flash-1019 as an upgraded version of Ling-3.1-flash. This profile remains separate from the existing Ling-3.1-flash and from the base checkpoint.
- Source: Model variant
- Parameter scale
- 560 billion total parameters, with 25 billion active per token.
- Source: Parameter scale
- Conflicting context figures
- The model card claims a 1-million-token context. config.json sets max_position_embeddings to 262,144 and explicitly sets rope_scaling to null. The supported usable length cannot be established safely from these conflicting values.
- Source: Conflicting context figures
- Weight format
- The model card lists BF16, F8_E4M3, and F32 tensors. The published configuration identifies FP8 quantization as e4m3.
- Source: Weight format
- Conflicting context limits
- Model card: 1 million tokens; config.json: max_position_embeddings 262,144, with rope_scaling explicitly set to null. The usable context limit remains unresolved.
- Source: Conflicting context limits
- Weight format
- Model card: BF16, F8_E4M3, and F32; configuration: FP8 quantization in e4m3 format
- Source: Weight format
- Artificial Analysis model identity
- id=539ed227-38f4-4bea-a015-117057c14b18; publicSlug=ling-3-1-flash-1019; title=Ling 3.1 Flash 1019; releaseSlug=ling-3-1-flash-rc5; releaseDate=2026-10-22 (Identity evidence for native mapping; benchmark values are not duplicated.)
- Source: Artificial Analysis model identity
Frequently asked questions about Ling 3.1 Flash 1019
Can I run Ling 3.1 Flash 1019 locally?
Yes, the weights are open. With 560B parameters it needs a lot of memory, more a server than a laptop.
Stated by inclusionAI
- Open weights
- yes
- License
- MIT
- Parameters
- 560B
- active per token
- 25B
Sources and data date
Show all 16 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 | 10 | 1 | 16 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 2 measurements are not yet assigned to a test series.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 29, 2026. 59 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Unresolved | Context limit across model card and config Note The card claims 1 million tokens, while the published configuration sets max_position_embeddings=262144 and explicitly sets rope_scaling to null. The usable runtime limit is not established. |
| Not published | Benchmark run configuration, sample counts, and confidence intervals Note The model card quotes five scores but does not publish run settings, n, or confidence intervals. Tables for other Ling checkpoints are not attributed to Ling-3.1-flash-1019. |
| Not found in the inspected sources | Public weight availability date Note No verified public release date was found in the model card and configuration. The model repository creation timestamp is not treated as a release date. |
| Not found in the inspected sources | Vals rows in captured payloads Note Nine complete Vals payloads dated 28 October were checked; no exact model ID or unambiguous model label. Limited to these saved benchmarks. |
| Unresolved | Uncaptured Arena Code/Speech leaderboards Note Text, Agent including Code/Chat/Work, and twelve WebDev views were captured. A separate general Code and Arena Speech leaderboard were not saved as complete tables. |
| Not published | Maximum output tokens per request Note AA publishes the combined context window and notes that the output limit may be lower and model-dependent. The captured card does not give an exact per-request output limit. |
| Not published | Operational request counts and confidence intervals Note The captured AA model card/payload does not publish request counts or confidence intervals for these operational values; no n or CI is inferred. |
| Not published | Output speed and latency distributions Note The exact AA card displays N/A for output tokens per second. The captured model row has no output-speed, first-chunk, response-time, or prompt-type distributions. |
| Additional source | Ling-3.1-flash-1019 official model card (retrieved October 29, 2026) · Ling-3.1-flash-1019 official model card · Editorial description reviewed October 29, 2026 |
| Additional source | Ling-3.1-flash-1019 configuration (retrieved October 29, 2026) · Ling-3.1-flash-1019 configuration · Editorial description reviewed October 29, 2026 |
| Additional source | Artificial Analysis (retrieved October 28, 2026; October 29, 2026)12 |
| Additional source | Artificial Analysis (retrieved October 29, 2026)123456789 |
| Additional source | Artificial Analysis model page (retrieved October 29, 2026) |
| Additional source | Model metadata (retrieved October 29, 2026)12 |