Model comparison
Amazon Nova Lite vs GPT-4.1 mini
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.7× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Amazon Nova Lite scores higher in 4 categories and GPT-4.1 mini in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-4.1 mini leads 73.7 to 59.3.
- The biggest single-benchmark swing is Omni-MATH: 23.3% for Amazon Nova Lite and 49.1% for GPT-4.1 mini.
- Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Lite | GPT-4.1 mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.9 | 33.6 |
| Released | 2024-12-03 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 33K |
| Input $ / M tokens | $0.06 | $0.40 |
| Output $ / M tokens | $0.24 | $1.60 |
| Results tracked | 34 | 47 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Lite leads
Amazon Nova Lite: 32.5 (#270), GPT-4.1 mini: 30.6 (#293)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Coding | 1239 | 1367 |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| SciCode | — | 40.4% |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| LiveBench Coding | 27.5% | — |
| CadEval | — | 16% |
| ALE-Bench | 236.25 | — |
Agentic & Tool Use Not comparable
Amazon Nova Lite: —, GPT-4.1 mini: 33.3 (#55)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |
Reasoning Amazon Nova Lite leads
Amazon Nova Lite: 19.3 (#260), GPT-4.1 mini: 10.8 (#340)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1349 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 48.6% |
| ARC-AGI-1 | — | 3.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| LiveBench Reasoning | 36.7% | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | 37.2% | — |
| LMCA | — | 21.1% |
| Epoch Capabilities Index | — | 135.01 |
| LiveBench | 36.4% | — |
Math Amazon Nova Lite leads
Amazon Nova Lite: 27.8 (#247), GPT-4.1 mini: 24.1 (#270)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| Omni-MATH | 23.3% | 49.1% |
| LMArena Math | 1227 | 1343 |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| OTIS Mock AIME 2024-2025 | — | 44.7% |
| LiveBench Math | 36.7% | — |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
Knowledge GPT-4.1 mini leads
Amazon Nova Lite: 26.3 (#259), GPT-4.1 mini: 34.7 (#194)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| MMLU-Pro | 60% | 78.3% |
| GPQA (HELM) | 39.7% | 61.4% |
| LMArena Expert | 1201 | 1338 |
| GPQA Diamond | — | 65.8% |
| Humanity's Last Exam | 3.6% | — |
| SimpleQA Verified | — | 12.7% |
| Vectara Hallucination Rate | 6.1% | — |
| MMLU | 77% | — |
Multimodal GPT-4.1 mini leads
Amazon Nova Lite: 25.5 (#123), GPT-4.1 mini: 35.8 (#82)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 990 | 1181 |
Multilingual GPT-4.1 mini leads
Amazon Nova Lite: 38.0 (#232), GPT-4.1 mini: 45.7 (#166)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1208 | 1318 |
| LMArena Chinese | 1225 | 1329 |
| LMArena French | 1237 | 1358 |
| LMArena German | 1229 | 1351 |
| LMArena Japanese | 1153 | 1290 |
| LMArena Korean | 1153 | 1298 |
| LMArena Russian | 1216 | 1324 |
| LMArena Spanish | 1226 | 1319 |
Instruction Following GPT-4.1 mini leads
Amazon Nova Lite: 59.3 (#255), GPT-4.1 mini: 73.7 (#118)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| IFEval | 77.6% | 90.4% |
| LMArena Instruction Following | 1205 | 1333 |
| LiveBench Instruction Following | 54.1% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), GPT-4.1 mini: 31.8 (#275)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1234 | 1344 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GPT-4.1 mini leads
Amazon Nova Lite: 42.1 (#237), GPT-4.1 mini: 48.6 (#199)
| Benchmark | Amazon Nova Lite | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1229 | 1340 |
| LMArena Creative Writing | 1197 | 1300 |
| WildBench | 75% | 83.8% |
| LMArena Multi-Turn | 1199 | 1354 |
| EQ-Bench Creative Writing | — | 1147 |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than GPT-4.1 mini?
GPT-4.1 mini is the stronger model overall, scoring 33.6 to 31.9 on the Noometry Index. Amazon Nova Lite costs 6.7× less per token, which makes it the better buy when GPT-4.1 mini's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Lite or GPT-4.1 mini?
Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.
Is Amazon Nova Lite or GPT-4.1 mini better for coding?
Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Lite and GPT-4.1 mini share?
23 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and GPT-4.1 mini has 47.