Amazon, proprietary
Amazon Nova Lite
Amazon Nova Lite by Amazon ranks 265th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.9. Its strongest category is multimodal, where it ranks 123rd. API pricing starts at $0.06 per million input tokens and $0.24 per million output tokens, with a 300K-token context window.
Last verified
Specifications
- Noometry rank
- #265 of 354
- Index score
- 31.9
- Evidence
- Confirmed 34 results
- Provider
- Amazon
- Released
- December 3, 2024
- Weights
- Proprietary
- Reasoning
- No
- Context window
- 300K
- Max output
- 10K
- Input price
- $0.06 / M
- Output price
- $0.24 / M
- Blended price
- $0.10 / M
- Output speed
- Not measured
- Value
- #19 of 219
- Knowledge cutoff
- October 2024
- Input
- text, image, video, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 32.5
- Reasoning 19.3
- Math 27.8
- Knowledge 26.3
- Multimodal 25.5
- Multilingual 38.0
- Instruction Following 59.3
- Long Context 37.4
- Writing & Preference 42.1
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 32.5 | #270 | 2 |
| Reasoning | 19.3 | #260 | 3 |
| Math | 27.8 | #247 | 3 |
| Knowledge | 26.3 | #259 | 5 |
| Multimodal | 25.5 | #123 | 1 |
| Multilingual | 38.0 | #232 | 1 |
| Instruction Following | 59.3 | #255 | 3 |
| Long Context | 37.4 | #217 | 1 |
| Writing & Preference | 42.1 | #237 | 5 |
Strengths and weaknesses
Categories where Amazon Nova Lite 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 |
|---|---|---|---|
| Long Context | 37.4 | −3.5 | #217 of 296, top 74% |
| Reasoning | 19.3 | −4.3 | #260 of 350, top 75% |
| Math | 27.8 | −8.7 | #247 of 327, top 76% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 25.5 | −13.0 | #123 of 128, top 97% |
| Instruction Following | 59.3 | −11.9 | #255 of 305, top 84% |
| Knowledge | 26.3 | −11.0 | #259 of 314, top 83% |
Closest competitors
The models ranked just above and below Amazon Nova Lite. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemini 1.5 Pro (May 2024) | #261 | 32.1 | — | — | Compare |
| Gemma 3 12B | #262 | 32.1 | $0.075 | — | Compare |
| Mistral Large | #263 | 31.9 | $3 | — | Compare |
| Qwen3-4B | #264 | 31.9 | — | — | Compare |
| Mistral Medium 3.1 | #266 | 31.9 | $0.80 | — | Compare |
| Qwen2.5 72B Instruct | #267 | 31.9 | $2.45 | — | Compare |
| Llama2 70b Steerlm Chat | #268 | 31.8 | — | — | Compare |
| Mistral Small 3.1 | #269 | 31.7 | $0.40 | — | 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 | 27.5% | #32 of 39, top 83% | Epoch AI | ||
| LMArena Coding | 1239 | #228 of 294, top 78% | LMArena | 2026-10-08 | |
| ALE-Bench | 236.25 | #101 of 105, top 97% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 36.7% | #28 of 39, top 72% | Epoch AI | ||
| LMArena Hard Prompts | 1220 | #230 of 297, top 78% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 37.2% | #33 of 39, top 85% | Epoch AI | ||
| LiveBench | 36.4% | #32 of 39, top 83% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Omni-MATH | 23.3% | #47 of 57, top 83% | HELM Capabilities | ||
| LiveBench Math | 36.7% | #29 of 39, top 75% | Epoch AI | ||
| LMArena Math | 1227 | #224 of 285, top 79% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Humanity's Last Exam | 3.6% | #40 of 41, top 98% | Epoch AI | ||
| MMLU-Pro | 60% | #44 of 58, top 76% | HELM Capabilities | ||
| Vectara Hallucination Rate (lower is better) | 6.1% | #22 of 96, top 23% | Vectara Hallucination Leaderboard | ||
| GPQA (HELM) | 39.7% | #42 of 57, top 74% | HELM Capabilities | ||
| LMArena Expert | 1201 | #222 of 273, top 82% | LMArena | 2026-10-08 | |
| MMLU | 77% | #28 of 81, top 35% | Epoch AI |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 990 | #118 of 122, top 97% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1208 | #232 of 297, top 79% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1225 | #221 of 285, top 78% | LMArena | 2026-10-08 | |
| LMArena French | 1237 | #186 of 223, top 84% | LMArena | 2026-10-08 | |
| LMArena German | 1229 | #184 of 231, top 80% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1153 | #174 of 211, top 83% | LMArena | 2026-10-08 | |
| LMArena Korean | 1153 | #176 of 213, top 83% | LMArena | 2026-10-08 | |
| LMArena Russian | 1216 | #230 of 283, top 82% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1226 | #190 of 226, top 85% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 54.1% | #35 of 39, top 90% | Epoch AI | ||
| IFEval | 77.6% | #48 of 57, top 85% | HELM Capabilities | ||
| LMArena Instruction Following | 1205 | #232 of 298, top 78% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1234 | #228 of 291, top 79% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1229 | #232 of 297, top 79% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1197 | #235 of 295, top 80% | LMArena | 2026-10-08 | |
| WildBench | 75% | #45 of 57, top 79% | HELM Capabilities | ||
| LMArena Multi-Turn | 1199 | #237 of 295, top 81% | LMArena | 2026-10-08 | |
| LiveBench Language | 25.9% | #30 of 39, top 77% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.06 | $0.24 | $0.015 | 2026-10-10 |
| openrouter | $0.06 | $0.24 | — | 2026-10-10 |
Compare Amazon Nova Lite
- Amazon Nova Lite vs Qwen3-4B
- Amazon Nova Lite vs Mistral Medium 3.1
- Amazon Nova Lite vs Mistral Large
- Amazon Nova Lite vs Qwen2.5 72B Instruct
- Amazon Nova Lite vs Gemma 3 12B
- Amazon Nova Lite vs Llama2 70b Steerlm Chat
- Amazon Nova Lite vs GPT-6 Astra
- Amazon Nova Lite vs Claude Fable 5.1
- Amazon Nova Lite vs Gemini 3.8 Flash
- Amazon Nova Lite vs Kimi K3
- Amazon Nova Lite vs Grok 4.6
- Amazon Nova Lite vs Qwen3.8 Max
- Amazon Nova Lite vs GLM-5.3
- Amazon Nova Lite vs Muse Spark 1.3
Frequently asked questions
How good is Amazon Nova Lite?
Amazon Nova Lite by Amazon ranks 265th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.9. Its strongest category is multimodal, where it ranks 123rd. API pricing starts at $0.06 per million input tokens and $0.24 per million output tokens, with a 300K-token context window.
How much does Amazon Nova Lite cost?
Amazon Nova Lite costs $0.06 per million input tokens and $0.24 per million output tokens on bedrock, with cached input at $0.015.
What is Amazon Nova Lite's context window?
Amazon Nova Lite accepts up to 300K tokens of input and can write up to 10K tokens in one response.
Is Amazon Nova Lite open source?
No. Amazon Nova Lite is proprietary and available only through Amazon's API and partner platforms.
What are Amazon Nova Lite's strengths and weaknesses?
Relative to other ranked models, Amazon Nova Lite places best in long context, reasoning, math and lowest in multimodal, instruction following, knowledge.
What is Amazon Nova Lite best at?
Its best category is multimodal, where it ranks 123rd on Noometry.