Language modelActive
Amazon Nova Micro
Amazon
- Released
- December 2024
- Data date
- September 8, 2026
- Speed
- 276.6 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
Amazon Nova Micro processes text only, while Amazon Nova Lite also accepts images and video. Its context window holds 128K tokens.
AWS lists amazon.nova-micro-v1:0 as an active Bedrock model identifier. The service does not support structured outputs or provide downloadable model weights.
Specifications and access
Page 1 of 3
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MMLU (Show measurement, test conditions, and source)
- Source value
- 77.6
- Score
- 77.6
- Metric
- percent
- Unit
- %
- Category
- knowledge
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot CoT
ARC-C (Show measurement, test conditions, and source)
- Source value
- 90.2
- Score
- 90.2
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot
DROP (Show measurement, test conditions, and source)
- Source value
- 79.3
- Score
- 79.3
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 6-shot CoT
GPQA (Show measurement, test conditions, and source)
- Source value
- 40
- Score
- 40
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot CoT; GPQA main set
MATH (Show measurement, test conditions, and source)
- Source value
- 69.3
- Score
- 69.3
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot CoT; MATH5k
GSM8K (Show measurement, test conditions, and source)
- Source value
- 92.3
- Score
- 92.3
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot CoT; test set
IFEval (Show measurement, test conditions, and source)
- Source value
- 87.2
- Score
- 87.2
- Metric
- percent
- Unit
- %
- Category
- instruction-following
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 0-shot; instruction-level loose accuracy
BBH (Show measurement, test conditions, and source)
- Source value
- 79.5
- Score
- 79.5
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; 3-shot CoT; macro average exact match
BFCL v3 overall (Show measurement, test conditions, and source)
- Source value
- 56.2
- Score
- 56.2
- Metric
- percent
- Unit
- %
- Category
- tool-use
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; BFCL v3; leaderboard state as of 2024-11-17; overall accuracy
- Context
- BFCL is a fast-moving live benchmark; the report freezes repository/leaderboard state at 2024-11-17.
BFCL v3 non-live AST (Show measurement, test conditions, and source)
- Source value
- 87.2
- Score
- 87.2
- Metric
- percent
- Unit
- %
- Category
- tool-use
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; BFCL v3; leaderboard state as of 2024-11-17; non-live function-call AST
- Context
- BFCL is a fast-moving live benchmark; the report freezes repository/leaderboard state at 2024-11-17.
BFCL v3 non-live execution (Show measurement, test conditions, and source)
- Source value
- 89.7
- Score
- 89.7
- Metric
- percent
- Unit
- %
- Category
- tool-use
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; BFCL v3; leaderboard state as of 2024-11-17; non-live function execution
- Context
- BFCL is a fast-moving live benchmark; the report freezes repository/leaderboard state at 2024-11-17.
BFCL v3 live overall (Show measurement, test conditions, and source)
- Source value
- 67.4
- Score
- 67.4
- Metric
- percent
- Unit
- %
- Category
- tool-use
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Amazon Nova technical report and model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Nova Micro; BFCL v3; leaderboard state as of 2024-11-17; live overall
- Context
- BFCL is a fast-moving live benchmark; the report freezes repository/leaderboard state at 2024-11-17.
Page 1 of 3
Popularity
39.3 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Speed | Amazon. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. |
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Research status | Research date September 8, 2026. 5 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | parameters-billions Original wording No exact value located in the checked primary model card/API documentation. |
| Not found in the inspected sources | active-parameters-billions Original wording No exact value located in the checked primary model card/API documentation. |
| Not found in the inspected sources | knowledge-cutoff Original wording No exact value located in the checked primary model card/API documentation. |
| Not found in the inspected sources | profile-benchmarks-additional Original wording The report contains additional figure-only runtime metrics (TTFT and total response time); only exact text-table rows were transcribed. |
| Additional source | Model metadata |
| Additional source | Context window data · Amazon Nova models · Editorial description reviewed October 4, 2026 |
| Additional source | Knowledge cutoff data · Amazon Bedrock model card for Amazon Nova Micro · Editorial description reviewed October 4, 2026 |
| Additional source | Amazon Nova technical report and model card (retrieved September 8, 2026) |
| Additional source | Model metadata (retrieved September 8, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |