Model comparison
Amazon Nova Lite vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 31.9 on the Noometry Index. Amazon Nova Lite costs 33× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and GPT-5.1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5.1 leads 83.9 to 59.3.
- The biggest single-benchmark swing is LiveBench Reasoning: 36.7% for Amazon Nova Lite and 95.8% for GPT-5.1.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Lite | GPT-5.1 | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.9 | 49.0 |
| Released | 2024-12-03 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.06 | $1.25 |
| Output $ / M tokens | $0.24 | $10 |
| Results tracked | 34 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
Amazon Nova Lite: 32.5 (#270), GPT-5.1: 46.4 (#66)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LiveBench Coding | 27.5% | 72.5% |
| LMArena Coding | 1239 | 1454 |
| ALE-Bench | 236.25 | 1,192 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| WeirdML | — | 60.8% |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, GPT-5.1: 32.7 (#60)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
Amazon Nova Lite: 19.3 (#260), GPT-5.1: 39.8 (#58)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LiveBench Reasoning | 36.7% | 95.8% |
| LMArena Hard Prompts | 1220 | 1457 |
| LiveBench Data Analysis | 37.2% | 72.1% |
| LiveBench | 36.4% | 78.8% |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| Chess Puzzles | — | 32% |
| EnigmaEval | — | 11.2% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 90.1% |
| LMCA | — | 43.9% |
| Epoch Capabilities Index | — | 149.64 |
| ForecastBench | — | 58.1 |
Math GPT-5.1 leads
Amazon Nova Lite: 27.8 (#247), GPT-5.1: 52.2 (#51)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| Omni-MATH | 23.3% | 46.4% |
| LiveBench Math | 36.7% | 94.5% |
| LMArena Math | 1227 | 1447 |
| OTIS Mock AIME 2024-2025 | — | 88.6% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
Amazon Nova Lite: 26.3 (#259), GPT-5.1: 50.6 (#71)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| Humanity's Last Exam | 3.6% | 23.7% |
| MMLU-Pro | 60% | 57.9% |
| Vectara Hallucination Rate | 6.1% | 10.9% |
| GPQA (HELM) | 39.7% | 44.2% |
| LMArena Expert | 1201 | 1470 |
| GPQA Diamond | — | 87.6% |
| SimpleQA Verified | — | 48% |
| MMLU | 77% | — |
Multimodal GPT-5.1 leads
Amazon Nova Lite: 25.5 (#123), GPT-5.1: 44.8 (#19)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LMArena Vision | 990 | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
Amazon Nova Lite: 38.0 (#232), GPT-5.1: 53.8 (#56)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1208 | 1431 |
| LMArena Chinese | 1225 | 1495 |
| LMArena French | 1237 | 1450 |
| LMArena German | 1229 | 1438 |
| LMArena Japanese | 1153 | 1453 |
| LMArena Korean | 1153 | 1401 |
| LMArena Russian | 1216 | 1435 |
| LMArena Spanish | 1226 | 1433 |
Instruction Following GPT-5.1 leads
Amazon Nova Lite: 59.3 (#255), GPT-5.1: 83.9 (#1)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LiveBench Instruction Following | 54.1% | 93.3% |
| IFEval | 77.6% | 93.5% |
| LMArena Instruction Following | 1205 | 1443 |
Long Context GPT-5.1 leads
Amazon Nova Lite: 37.4 (#217), GPT-5.1: 47.6 (#14)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1234 | 1447 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Amazon Nova Lite: 42.1 (#237), GPT-5.1: 64.5 (#55)
| Benchmark | Amazon Nova Lite | GPT-5.1 |
|---|---|---|
| LMArena Text | 1229 | 1443 |
| LMArena Creative Writing | 1197 | 1427 |
| WildBench | 75% | 86.3% |
| LMArena Multi-Turn | 1199 | 1450 |
| LiveBench Language | 25.9% | 80.2% |
Frequently asked questions
Is Amazon Nova Lite better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 31.9 on the Noometry Index. Amazon Nova Lite costs 33× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Lite or GPT-5.1?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is Amazon Nova Lite or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 32.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Lite and GPT-5.1 share?
33 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and GPT-5.1 has 63.