Model comparison
Amazon Nova Pro vs Phi 3 Small 8k Instruct
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
MicrosoftSummary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Amazon Nova Pro leads 64.9 to 51.9.
- The biggest single-benchmark swing is LiveBench Language: 37% for Amazon Nova Pro and 12.9% for Phi 3 Small 8k Instruct.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 31.0 | 29.3 |
| Released | 2024-12-03 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 38.1% | 20.3% |
| LMArena Coding | 1270 | 1101 |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Phi 3 Small 8k Instruct: —
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 32.6% | 15.9% |
| LMArena Hard Prompts | 1246 | 1100 |
| LiveBench Data Analysis | 48.3% | 30.3% |
| LiveBench | 43.5% | 24% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 123.8 | — |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math Too close to call
Amazon Nova Pro: 28.5 (#243), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 38% | 17.6% |
| LMArena Math | 1252 | 1151 |
| Omni-MATH | 24.2% | — |
Knowledge Phi 3 Small 8k Instruct leads
Amazon Nova Pro: 27.4 (#250), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1211 | 1067 |
| MMLU | 82% | 75.7% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Phi 3 Small 8k Instruct: —
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1234 | 1058 |
| LMArena Chinese | 1244 | 1061 |
| LMArena French | 1271 | 1135 |
| LMArena German | 1243 | 1080 |
| LMArena Japanese | 1200 | 966 |
| LMArena Korean | 1203 | 894 |
| LMArena Russian | 1240 | 1111 |
| LMArena Spanish | 1182 | 1111 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 47.2% |
| LMArena Instruction Following | 1235 | 1087 |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1255 | 1088 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Amazon Nova Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1259 | 1110 |
| LMArena Creative Writing | 1212 | 1083 |
| LMArena Multi-Turn | 1246 | 1068 |
| LiveBench Language | 37% | 12.9% |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Phi 3 Small 8k Instruct?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.3 on the Noometry Index.
Is Amazon Nova Pro or Phi 3 Small 8k Instruct better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 27.9 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Phi 3 Small 8k Instruct share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Phi 3 Small 8k Instruct has 32.