Amazon, proprietary
Amazon Nova Micro
Amazon Nova Micro by Amazon ranks 294th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.4. Its strongest category is agentic & tool use, where it ranks 132nd. API pricing starts at $0.035 per million input tokens and $0.14 per million output tokens, with a 128K-token context window.
Last verified
Specifications
- Noometry rank
- #294 of 354
- Index score
- 30.4
- Evidence
- Confirmed 32 results
- Provider
- Amazon
- Released
- December 3, 2024
- Weights
- Proprietary
- Reasoning
- No
- Context window
- 128K
- Max output
- 10K
- Input price
- $0.035 / M
- Output price
- $0.14 / M
- Blended price
- $0.0613 / M
- Output speed
- Not measured
- Value
- #7 of 219
- Knowledge cutoff
- October 2024
- Input
- text
Category scores
Each category score combines every public result we have in that category.
- Coding 30.5
- Agentic & Tool Use 22.1
- Reasoning 17.4
- Math 26.9
- Knowledge 29.6
- Multilingual 36.5
- Instruction Following 56.3
- Long Context 36.5
- Writing & Preference 39.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 30.5 | #295 | 2 |
| Agentic & Tool Use | 22.1 | #132 | 1 |
| Reasoning | 17.4 | #294 | 3 |
| Math | 26.9 | #254 | 3 |
| Knowledge | 29.6 | #237 | 4 |
| Multilingual | 36.5 | #239 | 1 |
| Instruction Following | 56.3 | #272 | 3 |
| Long Context | 36.5 | #229 | 1 |
| Writing & Preference | 39.5 | #247 | 5 |
Strengths and weaknesses
Categories where Amazon Nova Micro places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Knowledge | 29.6 | −7.8 | #237 of 314, top 76% |
| Long Context | 36.5 | −4.4 | #229 of 296, top 78% |
| Math | 26.9 | −9.7 | #254 of 327, top 78% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 56.3 | −15.0 | #272 of 305, top 90% |
| Coding | 30.5 | −8.2 | #295 of 340, top 87% |
| Agentic & Tool Use | 22.1 | −8.3 | #132 of 154, top 86% |
Closest competitors
The models ranked just above and below Amazon Nova Micro. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Codestral | #290 | 30.6 | $0.45 | 271 | Compare |
| Llama-3.3-70B-Instruct | #291 | 30.6 | $0.16 | — | Compare |
| GPT-4 Turbo | #292 | 30.5 | $15 | — | Compare |
| Qwen1.5-32B | #293 | 30.5 | — | — | Compare |
| Olmo 7b Instruct | #295 | 30.3 | — | — | Compare |
| Magistral Small | #296 | 30.2 | $0.75 | 0 | Compare |
| Qwen2.5 32B Instruct | #297 | 30.1 | $1.22 | — | Compare |
| Palm 2 | #298 | 30.0 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Coding | 20.2% | #35 of 39, top 90% | Epoch AI | ||
| LMArena Coding | 1218 | #234 of 294, top 80% | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | #43 of 49, top 88% | fc | Berkeley Function Calling Leaderboard |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 25.1% | #34 of 39, top 88% | Epoch AI | ||
| LMArena Hard Prompts | 1191 | #242 of 297, top 82% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 34% | #36 of 39, top 93% | Epoch AI | ||
| LiveBench | 29.6% | #34 of 39, top 88% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Omni-MATH | 21.4% | #49 of 57, top 86% | HELM Capabilities | ||
| LiveBench Math | 34.5% | #32 of 39, top 83% | Epoch AI | ||
| LMArena Math | 1206 | #231 of 285, top 82% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| MMLU-Pro | 51.1% | #51 of 58, top 88% | HELM Capabilities | ||
| Vectara Hallucination Rate (lower is better) | 5.5% | #15 of 96, top 16% | Vectara Hallucination Leaderboard | ||
| GPQA (HELM) | 38.3% | #45 of 57, top 79% | HELM Capabilities | ||
| LMArena Expert | 1184 | #224 of 273, top 83% | LMArena | 2026-10-08 | |
| MMLU | 70.8% | #42 of 81, top 52% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1186 | #239 of 297, top 81% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1209 | #230 of 285, top 81% | LMArena | 2026-10-08 | |
| LMArena French | 1238 | #185 of 223, top 83% | LMArena | 2026-10-08 | |
| LMArena German | 1192 | #193 of 231, top 84% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1154 | #173 of 211, top 82% | LMArena | 2026-10-08 | |
| LMArena Korean | 1150 | #178 of 213, top 84% | LMArena | 2026-10-08 | |
| LMArena Russian | 1185 | #243 of 283, top 86% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1225 | #191 of 226, top 85% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 48% | #37 of 39, top 95% | Epoch AI | ||
| IFEval | 76% | #49 of 57, top 86% | HELM Capabilities | ||
| LMArena Instruction Following | 1174 | #246 of 298, top 83% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1205 | #239 of 291, top 83% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1208 | #241 of 297, top 82% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1172 | #244 of 295, top 83% | LMArena | 2026-10-08 | |
| WildBench | 74.3% | #46 of 57, top 81% | HELM Capabilities | ||
| LMArena Multi-Turn | 1178 | #243 of 295, top 83% | LMArena | 2026-10-08 | |
| LiveBench Language | 15.8% | #36 of 39, top 93% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.035 | $0.14 | $0.00875 | 2026-10-10 |
| openrouter | $0.035 | $0.14 | — | 2026-10-10 |
Compare Amazon Nova Micro
- Amazon Nova Micro vs Qwen1.5-32B
- Amazon Nova Micro vs Olmo 7b Instruct
- Amazon Nova Micro vs GPT-4 Turbo
- Amazon Nova Micro vs Magistral Small
- Amazon Nova Micro vs Llama-3.3-70B-Instruct
- Amazon Nova Micro vs Qwen2.5 32B Instruct
- Amazon Nova Micro vs GPT-6 Astra
- Amazon Nova Micro vs Claude Fable 5.1
- Amazon Nova Micro vs Gemini 3.8 Flash
- Amazon Nova Micro vs Kimi K3
- Amazon Nova Micro vs Grok 4.6
- Amazon Nova Micro vs Qwen3.8 Max
- Amazon Nova Micro vs GLM-5.3
- Amazon Nova Micro vs Muse Spark 1.3
Frequently asked questions
How good is Amazon Nova Micro?
Amazon Nova Micro by Amazon ranks 294th of 354 ranked models on the Noometry Index as of October 2026, with a score of 30.4. Its strongest category is agentic & tool use, where it ranks 132nd. API pricing starts at $0.035 per million input tokens and $0.14 per million output tokens, with a 128K-token context window.
How much does Amazon Nova Micro cost?
Amazon Nova Micro costs $0.035 per million input tokens and $0.14 per million output tokens on bedrock, with cached input at $0.00875.
What is Amazon Nova Micro's context window?
Amazon Nova Micro accepts up to 128K tokens of input and can write up to 10K tokens in one response.
Is Amazon Nova Micro open source?
No. Amazon Nova Micro is proprietary and available only through Amazon's API and partner platforms.
What are Amazon Nova Micro's strengths and weaknesses?
Relative to other ranked models, Amazon Nova Micro places best in knowledge, long context, math and lowest in instruction following, coding, agentic & tool use.
What is Amazon Nova Micro best at?
Its best category is agentic & tool use, where it ranks 132nd on Noometry.