Model comparison
Amazon Nova Lite vs Phi 3 Mini 128k Instruct
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Amazon Nova Lite scores higher in 5 categories and Phi 3 Mini 128k Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Lite leads 42.1 to 27.1.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 31.9 | 29.7 |
| Released | 2024-12-03 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 19 |
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), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1239 | 1039 |
| BigCodeBench Instruct | — | 29.6% |
| LiveBench Coding | 27.5% | — |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 236.25 | — |
Reasoning Too close to call
Amazon Nova Lite: 19.3 (#260), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1028 |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| LiveBench | 36.4% | — |
Math Phi 3 Mini 128k Instruct leads
Amazon Nova Lite: 27.8 (#247), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1227 | 1089 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
Knowledge Too close to call
Amazon Nova Lite: 26.3 (#259), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1201 | 984 |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), Phi 3 Mini 128k Instruct: —
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Amazon Nova Lite leads
Amazon Nova Lite: 38.0 (#232), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1208 | 1000 |
| LMArena Chinese | 1225 | 1016 |
| LMArena French | 1237 | 1039 |
| LMArena German | 1229 | 1006 |
| LMArena Japanese | 1153 | 899 |
| LMArena Korean | 1153 | 856 |
| LMArena Russian | 1216 | 1004 |
| LMArena Spanish | 1226 | 1059 |
Instruction Following Amazon Nova Lite leads
Amazon Nova Lite: 59.3 (#255), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1205 | 1023 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Amazon Nova Lite leads
Amazon Nova Lite: 37.4 (#217), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1234 | 996 |
Writing & Preference Amazon Nova Lite leads
Amazon Nova Lite: 42.1 (#237), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Amazon Nova Lite | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1229 | 1050 |
| LMArena Creative Writing | 1197 | 1024 |
| LMArena Multi-Turn | 1199 | 989 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Phi 3 Mini 128k Instruct?
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.7 on the Noometry Index.
Is Amazon Nova Lite or Phi 3 Mini 128k Instruct better for coding?
Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 28.8 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.