Model comparison
Amazon Nova Experimental Chat 10 20 vs phi-3-medium 14B
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Amazon Nova Experimental Chat 10 20 leads 38.5 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 42.1 | 29.7 |
| Released | — | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 41.6 (#123), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1412 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Amazon Nova Experimental Chat 10 20: 28.4 (#106), phi-3-medium 14B: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1396 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 39.0 (#119), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1425 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Amazon Nova Experimental Chat 10 20 leads
Amazon Nova Experimental Chat 10 20: 38.5 (#144), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1386 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Amazon Nova Experimental Chat 10 20: 49.5 (#131), phi-3-medium 14B: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1404 | — |
| LMArena French | 1425 | — |
| LMArena German | 1391 | — |
| LMArena Japanese | 1360 | — |
| LMArena Korean | 1324 | — |
| LMArena Russian | 1371 | — |
| LMArena Spanish | 1382 | — |
Instruction Following Not comparable
Amazon Nova Experimental Chat 10 20: 72.1 (#141), phi-3-medium 14B: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1365 | — |
Long Context Not comparable
Amazon Nova Experimental Chat 10 20: 41.7 (#133), phi-3-medium 14B: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1370 | — |
Writing & Preference Not comparable
Amazon Nova Experimental Chat 10 20: 56.6 (#136), phi-3-medium 14B: —
| Benchmark | Amazon Nova Experimental Chat 10 20 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1394 | — |
| LMArena Creative Writing | 1318 | — |
| LMArena Multi-Turn | 1364 | — |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 20 better than phi-3-medium 14B?
Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 29.7 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 20 or phi-3-medium 14B better for coding?
Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 36.8 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 20 and phi-3-medium 14B share?
0 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and phi-3-medium 14B has 13.