# Amazon Nova Lite vs Kimi K3

> Kimi K3 is the stronger model overall, scoring 59.5 to 31.9 on the Noometry Index. Amazon Nova Lite costs 57× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-kimi-k3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and Kimi K3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 27.8.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 300K.
- Kimi K3 has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| Provider | Amazon | Moonshot AI |
| Noometry Index | 31.9 | 59.5 |
| Rank | 265 | 15 |
| Context | 300K | 1.05M |
| Input $/M | $0.06 | $3 |
| Output $/M | $0.24 | $15 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- Kimi K3: 61.0 (#10)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Coding | 1239 | 1508 |
| ALE-Bench | 236.25 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
| LiveBench Coding | 27.5% | — |

## Agentic & Tool Use

- Amazon Nova Lite: —
- Kimi K3: 41.8 (#20)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- Kimi K3: 63.0 (#17)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1496 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| NYT Connections (extended) | — | 93.6% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
| ForecastBench | — | 61.1 |
| LiveBench | 36.4% | — |

## Math

- Amazon Nova Lite: 27.8 (#247)
- Kimi K3: 74.2 (#16)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Math | 1227 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 87% |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- Kimi K3: 63.2 (#21)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Expert | 1201 | 1521 |
| GPQA Diamond | — | 93.1% |
| Humanity's Last Exam | 3.6% | — |
| SimpleQA Verified | — | 50.6% |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- Kimi K3: 37.8 (#70)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Vision | 990 | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- Kimi K3: 56.3 (#21)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1208 | 1466 |
| LMArena Chinese | 1225 | 1529 |
| LMArena French | 1237 | 1491 |
| LMArena German | 1229 | 1488 |
| LMArena Japanese | 1153 | 1487 |
| LMArena Korean | 1153 | 1458 |
| LMArena Russian | 1216 | 1482 |
| LMArena Spanish | 1226 | 1472 |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- Kimi K3: 77.7 (#14)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1205 | 1483 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- Kimi K3: 45.8 (#29)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1234 | 1494 |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- Kimi K3: 76.6 (#4)

| Benchmark | Amazon Nova Lite | Kimi K3 |
|---|---|---|
| LMArena Text | 1229 | 1476 |
| LMArena Creative Writing | 1197 | 1454 |
| LMArena Multi-Turn | 1199 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| WildBench | 75% | — |
| EQ-Bench 4 | — | 1339 |
| LiveBench Language | 25.9% | — |

## FAQ

### Is Amazon Nova Lite better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 31.9 on the Noometry Index. Amazon Nova Lite costs 57× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Lite or Kimi K3?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Kimi K3 lists at $3 and $15.

### Is Amazon Nova Lite or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 32.5 in the Noometry coding category.

### Which has the bigger context window?

Kimi K3 does, with 1.05M tokens against 300K.

### How many benchmarks do Amazon Nova Lite and Kimi K3 share?

18 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Kimi K3 has 53.