# Amazon Nova Lite vs GPT-5 Mini

> GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.5× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/amazon-nova-lite-vs-gpt-5-mini
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and GPT-5 Mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 26.3.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 72.2% for GPT-5 Mini.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 300K.

## Snapshot

| | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.9 | 41.8 |
| Rank | 265 | 128 |
| Context | 300K | 400K |
| Input $/M | $0.06 | $0.25 |
| Output $/M | $0.24 | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Lite: 32.5 (#270)
- GPT-5 Mini: 40.1 (#146)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1239 | 1406 |
| ALE-Bench | 236.25 | 799.77 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| LiveBench Coding | 27.5% | — |
| AlgoTune | — | 1.38 |

## Agentic & Tool Use

- Amazon Nova Lite: —
- GPT-5 Mini: 31.1 (#70)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- Amazon Nova Lite: 19.3 (#260)
- GPT-5 Mini: 23.9 (#168)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1380 |
| ARC-AGI-2 | — | 4.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 34.2% |
| Epoch Capabilities Index | — | 145.52 |
| ForecastBench | — | 61 |
| LiveBench | 36.4% | — |

## Math

- Amazon Nova Lite: 27.8 (#247)
- GPT-5 Mini: 46.7 (#69)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| Omni-MATH | 23.3% | 72.2% |
| LMArena Math | 1227 | 1378 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Amazon Nova Lite: 26.3 (#259)
- GPT-5 Mini: 45.6 (#86)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| Humanity's Last Exam | 3.6% | 19.4% |
| MMLU-Pro | 60% | 83.5% |
| Vectara Hallucination Rate | 6.1% | 12.9% |
| GPQA (HELM) | 39.7% | 75.6% |
| LMArena Expert | 1201 | 1379 |
| GPQA Diamond | — | 75% |
| SimpleQA Verified | — | 21.6% |
| Confabulations | — | 13.3% |
| MMLU | 77% | — |

## Multimodal

- Amazon Nova Lite: 25.5 (#123)
- GPT-5 Mini: 35.6 (#85)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 990 | 1202 |
| VPCT | — | 40.2% |

## Multilingual

- Amazon Nova Lite: 38.0 (#232)
- GPT-5 Mini: 48.9 (#137)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1208 | 1363 |
| LMArena Chinese | 1225 | 1385 |
| LMArena French | 1237 | 1386 |
| LMArena German | 1229 | 1366 |
| LMArena Japanese | 1153 | 1341 |
| LMArena Korean | 1153 | 1308 |
| LMArena Russian | 1216 | 1362 |
| LMArena Spanish | 1226 | 1355 |

## Instruction Following

- Amazon Nova Lite: 59.3 (#255)
- GPT-5 Mini: 76.2 (#46)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| IFEval | 77.6% | 92.7% |
| LMArena Instruction Following | 1205 | 1357 |
| LiveBench Instruction Following | 54.1% | — |

## Long Context

- Amazon Nova Lite: 37.4 (#217)
- GPT-5 Mini: 41.9 (#132)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1234 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- Amazon Nova Lite: 42.1 (#237)
- GPT-5 Mini: 55.2 (#148)

| Benchmark | Amazon Nova Lite | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1229 | 1373 |
| LMArena Creative Writing | 1197 | 1325 |
| WildBench | 75% | 85.5% |
| LMArena Multi-Turn | 1199 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| LiveBench Language | 25.9% | — |

## FAQ

### Is Amazon Nova Lite better than GPT-5 Mini?

GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.5× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.

### Which is cheaper, Amazon Nova Lite or GPT-5 Mini?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; GPT-5 Mini lists at $0.25 and $2.

### Is Amazon Nova Lite or GPT-5 Mini better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 32.5 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Mini does, with 400K tokens against 300K.

### How many benchmarks do Amazon Nova Lite and GPT-5 Mini share?

26 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and GPT-5 Mini has 60.