Model comparison
Amazon Nova Micro vs Phi 3 Mini 4k Instruct
Amazon Nova Micro is the stronger model overall, scoring 29.9 to 27.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
MicrosoftSummary
- They share 25 benchmarks with published results for both. Amazon Nova Micro scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Micro leads 39.7 to 27.7.
- The biggest single-benchmark swing is LiveBench Math: 34.5% for Amazon Nova Micro and 15.7% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 29.9 | 27.4 |
| Released | 2024-12-03 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Micro leads
Amazon Nova Micro: 30.0 (#289), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 20.2% | 15.5% |
| LMArena Coding | 1218 | 1093 |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 21.9 (#125), Phi 3 Mini 4k Instruct: —
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 16.7 (#289), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 25.1% | 26.8% |
| LMArena Hard Prompts | 1191 | 1072 |
| LiveBench Data Analysis | 34% | 34.7% |
| LiveBench | 29.6% | 22.4% |
| Chess Puzzles | — | 0% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Too close to call
Amazon Nova Micro: 24.9 (#252), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 34.5% | 15.7% |
| LMArena Math | 1206 | 1111 |
| Omni-MATH | 21.4% | — |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.2 (#231), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1184 | 1045 |
| MMLU | 70.8% | 68.8% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Amazon Nova Micro leads
Amazon Nova Micro: 36.7 (#234), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1186 | 1021 |
| LMArena Chinese | 1209 | 1021 |
| LMArena French | 1237 | 1075 |
| LMArena German | 1192 | 1044 |
| LMArena Japanese | 1154 | 935 |
| LMArena Korean | 1150 | 905 |
| LMArena Russian | 1185 | 1022 |
| LMArena Spanish | 1225 | 1084 |
Instruction Following Amazon Nova Micro leads
Amazon Nova Micro: 56.6 (#267), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 48% | 39.1% |
| LMArena Instruction Following | 1174 | 1053 |
| IFEval | 76% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#224), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1206 | 1044 |
Writing & Preference Amazon Nova Micro leads
Amazon Nova Micro: 39.7 (#242), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Amazon Nova Micro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1208 | 1073 |
| LMArena Creative Writing | 1172 | 1037 |
| LMArena Multi-Turn | 1178 | 1018 |
| LiveBench Language | 15.8% | 9.2% |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than Phi 3 Mini 4k Instruct?
Amazon Nova Micro is the stronger model overall, scoring 29.9 to 27.4 on the Noometry Index.
Is Amazon Nova Micro or Phi 3 Mini 4k Instruct better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.0 versus 26.1 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.