Model comparison
Amazon Nova Lite vs GPT-5 Nano
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Amazon Nova Lite scores higher in 3 categories and GPT-5 Nano in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.2 to 59.6.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 54.6% for GPT-5 Nano.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.05 / $0.40 for GPT-5 Nano.
- GPT-5 Nano accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Lite | GPT-5 Nano | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.4 | 33.4 |
| Released | 2024-12-03 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.06 | $0.05 |
| Output $ / M tokens | $0.24 | $0.40 |
| Results tracked | 34 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
Amazon Nova Lite: 32.0 (#266), GPT-5 Nano: 33.3 (#248)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1239 | 1351 |
| ALE-Bench | 236.25 | 718.67 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| LiveBench Coding | 27.5% | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, GPT-5 Nano: 25.6 (#99)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
Reasoning Amazon Nova Lite leads
Amazon Nova Lite: 18.5 (#257), GPT-5 Nano: 16.4 (#291)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1329 |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.39 |
| ForecastBench | — | 59.1 |
| LiveBench | 36.4% | — |
Math GPT-5 Nano leads
Amazon Nova Lite: 25.8 (#243), GPT-5 Nano: 29.1 (#221)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| Omni-MATH | 23.3% | 54.6% |
| LMArena Math | 1227 | 1318 |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5 Nano leads
Amazon Nova Lite: 26.0 (#254), GPT-5 Nano: 35.8 (#166)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| MMLU-Pro | 60% | 77.8% |
| Vectara Hallucination Rate | 6.1% | 10.5% |
| GPQA (HELM) | 39.7% | 67.9% |
| LMArena Expert | 1201 | 1321 |
| GPQA Diamond | — | 69.4% |
| Humanity's Last Exam | 3.6% | — |
| SimpleQA Verified | — | 11.7% |
| MMLU | 77% | — |
Multimodal GPT-5 Nano leads
Amazon Nova Lite: 25.0 (#118), GPT-5 Nano: 30.7 (#102)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 990 | 1159 |
| VPCT | — | 37.2% |
Multilingual GPT-5 Nano leads
Amazon Nova Lite: 38.2 (#227), GPT-5 Nano: 45.5 (#167)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1208 | 1313 |
| LMArena Chinese | 1225 | 1355 |
| LMArena German | 1229 | 1329 |
| LMArena Korean | 1153 | 1269 |
| LMArena Russian | 1216 | 1296 |
| LMArena Spanish | 1225 | 1360 |
| LMArena French | 1237 | — |
| LMArena Japanese | 1153 | — |
Instruction Following GPT-5 Nano leads
Amazon Nova Lite: 59.6 (#250), GPT-5 Nano: 75.2 (#72)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| IFEval | 77.6% | 93.2% |
| LMArena Instruction Following | 1205 | 1306 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#212), GPT-5 Nano: 31.3 (#275)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1234 | 1313 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.3 (#232), GPT-5 Nano: 39.4 (#244)
| Benchmark | Amazon Nova Lite | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1229 | 1320 |
| LMArena Creative Writing | 1197 | 1250 |
| WildBench | 75% | 80.6% |
| LMArena Multi-Turn | 1199 | 1311 |
| EQ-Bench Creative Writing | — | 705 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than GPT-5 Nano?
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.4 on the Noometry Index.
Which is cheaper, Amazon Nova Lite or GPT-5 Nano?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; GPT-5 Nano lists at $0.05 and $0.40.
Is Amazon Nova Lite or GPT-5 Nano better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.3 versus 32.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Lite and GPT-5 Nano share?
23 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and GPT-5 Nano has 48.