# Amazon Nova Lite vs Gemini 3.1 Flash Lite

> Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 31.9 on the Noometry Index. Amazon Nova Lite costs 5.4× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-gemini-3-1-flash-lite
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and Gemini 3.1 Flash Lite in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 42.1.
- The biggest single-benchmark swing is Humanity's Last Exam: 3.6% for Amazon Nova Lite and 8.6% for Gemini 3.1 Flash Lite.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 300K.

## Snapshot

| | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| Provider | Amazon | Google |
| Noometry Index | 31.9 | 40.8 |
| Rank | 265 | 144 |
| Context | 300K | 1.05M |
| Input $/M | $0.06 | $0.25 |
| Output $/M | $0.24 | $1.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- Gemini 3.1 Flash Lite: 37.8 (#188)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Coding | 1239 | 1400 |
| ALE-Bench | 236.25 | 797.73 |
| LMArena WebDev | — | 1256 |
| SciCode | — | 41.9% |
| WeirdML | — | 52.2% |
| LiveBench Coding | 27.5% | — |

## Agentic & Tool Use

- Amazon Nova Lite: —
- Gemini 3.1 Flash Lite: 30.2 (#79)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| DeepResearch Bench | — | 37.3% |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- Gemini 3.1 Flash Lite: 22.9 (#186)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1407 |
| Kagi LLM Benchmark | — | 67.2% |
| NYT Connections (extended) | — | 8.2% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 25% |
| EnigmaEval | — | 3% |
| Thematic Generalization | — | 63.3% |
| LiveBench Reasoning | 36.7% | — |
| DTBench | — | 76.8% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 35% |
| Epoch Capabilities Index | — | 144.47 |
| ForecastBench | — | 54.4 |
| LiveBench | 36.4% | — |

## Math

- Amazon Nova Lite: 27.8 (#247)
- Gemini 3.1 Flash Lite: 40.7 (#90)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Math | 1227 | 1428 |
| FrontierMath (Tiers 1-3) | — | 27.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- Gemini 3.1 Flash Lite: 41.9 (#104)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| Humanity's Last Exam | 3.6% | 8.6% |
| Vectara Hallucination Rate | 6.1% | 8.2% |
| LMArena Expert | 1201 | 1398 |
| GPQA Diamond | — | 81.8% |
| MMLU-Pro | 60% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- Gemini 3.1 Flash Lite: 39.4 (#60)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | 990 | 1240 |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- Gemini 3.1 Flash Lite: 52.3 (#86)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1208 | 1411 |
| LMArena Chinese | 1225 | 1461 |
| LMArena French | 1237 | 1424 |
| LMArena German | 1229 | 1429 |
| LMArena Japanese | 1153 | 1413 |
| LMArena Korean | 1153 | 1392 |
| LMArena Russian | 1216 | 1420 |
| LMArena Spanish | 1226 | 1421 |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- Gemini 3.1 Flash Lite: 72.7 (#131)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1205 | 1377 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- Gemini 3.1 Flash Lite: 42.5 (#122)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1234 | 1394 |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- Gemini 3.1 Flash Lite: 60.9 (#94)

| Benchmark | Amazon Nova Lite | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1229 | 1416 |
| LMArena Creative Writing | 1197 | 1401 |
| LMArena Multi-Turn | 1199 | 1417 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |

## FAQ

### Is Amazon Nova Lite better than Gemini 3.1 Flash Lite?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 31.9 on the Noometry Index. Amazon Nova Lite costs 5.4× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Lite or Gemini 3.1 Flash Lite?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Gemini 3.1 Flash Lite lists at $0.25 and $1.50.

### Is Amazon Nova Lite or Gemini 3.1 Flash Lite better for coding?

Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 32.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 300K.

### How many benchmarks do Amazon Nova Lite and Gemini 3.1 Flash Lite share?

21 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Gemini 3.1 Flash Lite has 38.