Model comparison
Amazon Nova Micro vs Phi-2
Amazon Nova Micro has enough public results to be ranked (#290); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both.
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Phi-2 | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 29.9 | — |
| Released | 2024-12-03 | 2023-12-12 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Amazon Nova Micro: 30.0 (#289), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LiveBench Coding | 20.2% | — |
| LMArena Coding | 1218 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 21.9 (#125), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Not comparable
Amazon Nova Micro: 16.7 (#289), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LiveBench Reasoning | 25.1% | — |
| LMArena Hard Prompts | 1191 | — |
| LiveBench Data Analysis | 34% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| LiveBench | 29.6% | — |
| WinoGrande | — | 54.7% |
Math Not comparable
Amazon Nova Micro: 24.9 (#252), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| LMArena Math | 1206 | — |
Knowledge Not comparable
Amazon Nova Micro: 29.2 (#231), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| MMLU | 70.8% | 58.4% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1184 | — |
| ARC (AI2) Challenge | — | 75.9% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Amazon Nova Micro: 36.7 (#234), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LMArena Non-English | 1186 | — |
| LMArena Chinese | 1209 | — |
| LMArena French | 1237 | — |
| LMArena German | 1192 | — |
| LMArena Japanese | 1154 | — |
| LMArena Korean | 1150 | — |
| LMArena Russian | 1185 | — |
| LMArena Spanish | 1225 | — |
Instruction Following Not comparable
Amazon Nova Micro: 56.6 (#267), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
| LMArena Instruction Following | 1174 | — |
Long Context Not comparable
Amazon Nova Micro: 36.5 (#224), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1206 | — |
Writing & Preference Not comparable
Amazon Nova Micro: 39.7 (#242), Phi-2: —
| Benchmark | Amazon Nova Micro | Phi-2 |
|---|---|---|
| LMArena Text | 1208 | — |
| LMArena Creative Writing | 1172 | — |
| WildBench | 74.3% | — |
| LMArena Multi-Turn | 1178 | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Phi-2?
Amazon Nova Micro has enough public results to be ranked (#290); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Amazon Nova Micro and Phi-2 share?
1 benchmark has published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Phi-2 has 11.