Model comparison
Amazon Nova Lite vs phi-3-medium 14B
Amazon Nova Lite is the stronger model overall, scoring 31.9 to 29.7 on the Noometry Index.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both. Amazon Nova Lite scores higher in 2 categories and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Lite leads 26.3 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | phi-3-medium 14B | |
|---|---|---|
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Amazon Nova Lite: 32.5 (#270), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 27.5% | — |
| LMArena Coding | 1239 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 236.25 | — |
Reasoning Not comparable
Amazon Nova Lite: 19.3 (#260), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LiveBench Reasoning | 36.7% | — |
| LMArena Hard Prompts | 1220 | — |
| LiveBench Data Analysis | 37.2% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| LiveBench | 36.4% | — |
| WinoGrande | — | 81.5% |
Math Too close to call
Amazon Nova Lite: 27.8 (#247), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
| LMArena Math | 1227 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Amazon Nova Lite leads
Amazon Nova Lite: 26.3 (#259), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| MMLU | 77% | 78% |
| GPQA Diamond | — | 27.6% |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| LMArena Expert | 1201 | — |
| ARC (AI2) Challenge | — | 91.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Amazon Nova Lite: 25.5 (#123), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 990 | — |
Multilingual Not comparable
Amazon Nova Lite: 38.0 (#232), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1208 | — |
| LMArena Chinese | 1225 | — |
| LMArena French | 1237 | — |
| LMArena German | 1229 | — |
| LMArena Japanese | 1153 | — |
| LMArena Korean | 1153 | — |
| LMArena Russian | 1216 | — |
| LMArena Spanish | 1226 | — |
Instruction Following Not comparable
Amazon Nova Lite: 59.3 (#255), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
| LMArena Instruction Following | 1205 | — |
Long Context Not comparable
Amazon Nova Lite: 37.4 (#217), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1234 | — |
Writing & Preference Not comparable
Amazon Nova Lite: 42.1 (#237), phi-3-medium 14B: —
| Benchmark | Amazon Nova Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1229 | — |
| LMArena Creative Writing | 1197 | — |
| WildBench | 75% | — |
| LMArena Multi-Turn | 1199 | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than phi-3-medium 14B?
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-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 32.5 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and phi-3-medium 14B share?
1 benchmark has published results for both models. Amazon Nova Lite has 34 scored results on Noometry and phi-3-medium 14B has 13.