Cohere LabsLanguage modelOpen weights
Tiny Aya Global
Tiny Aya Global has no overall index value yet because there are too few independent benchmark results.
30out of 100new calculation
based on two data groups, mostly search, range 20 to 40
Summary
Tiny Aya Global balances its multilingual focus across world regions. Cohere Labs offers it alongside three region-specialized Tiny Aya models. The family covers more than 70 languages, and Global contains 3.35 billion parameters.
The local weights use CC BY-NC 4.0 with additional Cohere usage terms. The license limits use to non-commercial purposes.
On this page
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 264 published benchmark results
Page 1 of 22
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
- 0
- 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: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/81444bc8-72f9-4a2d-ad43-27e3f0d2f461/tiny-aya-global/tiny-aya-global. Source model name: Tiny Aya Global. Provider reported by source: Cohere. Model snapshot: Tiny Aya Global. 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: non-reasoning. Reasoning effort: none. Score display: 0.0%. 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:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. 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: non-reasoning. Reasoning effort: none
- 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.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 20.1360544218
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- 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: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/81444bc8-72f9-4a2d-ad43-27e3f0d2f461/tiny-aya-global/tiny-aya-global. Source model name: Tiny Aya Global. Provider reported by source: Cohere. Model snapshot: Tiny Aya Global. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 20.1%. 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-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). AA marks this model variant as non-reasoning and reports 0 reasoning tokens. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.. This result is retained as historical evidence and is not interchangeable with current results.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 20.1360544218
- Metric
- IFBench prompt-level loose accuracy (pass@1)
- Unit
- %
- Benchmark version
- AA test set: 294 questions
- Category
- general
- 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: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/81444bc8-72f9-4a2d-ad43-27e3f0d2f461/tiny-aya-global/tiny-aya-global. Source model name: Tiny Aya Global. Provider reported by source: Cohere. Model snapshot: Tiny Aya Global. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none. Score display: 20.1%. 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-ifbench:AA test set: 294 questions:standalone:non-reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Tiny Aya Global (release tiny-aya-global, row tiny-aya-global, UUID 81444bc8-72f9-4a2d-ad43-27e3f0d2f461, reasoning=false, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Reasoning effort: none
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.
NormAd English Stories, Europe accuracy (Show measurement, test conditions, and source)
- Source value
- 74.91
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd English Stories, West Asia accuracy (Show measurement, test conditions, and source)
- Source value
- 68.17
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd English Stories, South Asia accuracy (Show measurement, test conditions, and source)
- Source value
- 69.03
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd English Stories, Asia-Pacific accuracy (Show measurement, test conditions, and source)
- Source value
- 77.73
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd English Stories, Africa accuracy (Show measurement, test conditions, and source)
- Source value
- 71.43
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd English Stories, Americas accuracy (Show measurement, test conditions, and source)
- Source value
- 73.53
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 16, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 16; NormAd per-region accuracy. Stories are in English. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd Source-Language Stories, Europe accuracy (Show measurement, test conditions, and source)
- Source value
- 72.27
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 17, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 17; NormAd per-region accuracy. Stories are in each country's official language. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd Source-Language Stories, West Asia accuracy (Show measurement, test conditions, and source)
- Source value
- 67.44
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 17, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 17; NormAd per-region accuracy. Stories are in each country's official language. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
NormAd Source-Language Stories, South Asia accuracy (Show measurement, test conditions, and source)
- Source value
- 69.07
- Metric
- accuracy
- Unit
- %
- Benchmark version
- NormAd, Table 17, arXiv:2603.11510v1
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Cohere Labs, Tiny Aya: Bridging Scale and Multilingual Depth, arXiv:2603.11510v1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact Tiny Aya Global row from Table 17; NormAd per-region accuracy. Stories are in each country's official language. The paper maps 75 countries to languages but does not disclose this row's scored-example denominator or prompt and decoding details.
Page 1 of 22
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 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 20, 2026
Tiny Aya GlobalGPT-5 Pro 30Index-Translate-2B 30Apertus 70B 30Falcon 180B 30
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
- 2November 1, 2026: Method version 4 (common scale, shrinkage)
- 3November 9, 2026: New topics measurement V20 (daily quorum, short forms)
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 Tiny Aya Global, chosen by model line, developer, size, price and release date.
- Tiny Aya EarthCohere Labs · same developer
- Tiny Aya FireCohere Labs · same developer
- Tiny Aya WaterCohere Labs · same developer
- Qwen3.5 4BAlibaba · similar size
- DeepSeek OCR 2DeepSeek · similar size
- Ministral 3 3BMistral AI · similar size
- Jamba2-3BAI21 · similar size
- K2 Horizon 3.7BInstitute of Foundation Models · similar size
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
- Shutdown
- None announced
- no source
Further details
Frequently asked questions about Tiny Aya Global
Can I run Tiny Aya Global locally?
Yes, the weights are open.
Stated by Cohere Labs
- Open weights
- yes
- License
- CC BY-NC 4.0 with Cohere usage terms
- Parameters
- 3.4B
- active per token
- n/a
Sources and data date
Show all 23 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 | 1 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.