Model comparison
Nova 2 Lite vs phi-3-medium 14B
Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Nova 2 Lite | phi-3-medium 14B | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 39.7 | 29.7 |
| Released | 2025-12-01 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 19 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Nova 2 Lite: 40.7 (#134), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1385 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Nova 2 Lite: 24.1 (#121), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Not comparable
Nova 2 Lite: 27.5 (#118), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1364 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Nova 2 Lite leads
Nova 2 Lite: 37.5 (#156), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1359 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Nova 2 Lite leads
Nova 2 Lite: 43.0 (#94), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| Vectara Hallucination Rate | 5.1% | — |
| LMArena Expert | 1358 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Nova 2 Lite: 47.1 (#153), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1337 | — |
| LMArena Chinese | 1364 | — |
| LMArena French | 1381 | — |
| LMArena German | 1343 | — |
| LMArena Japanese | 1271 | — |
| LMArena Korean | 1284 | — |
| LMArena Russian | 1343 | — |
| LMArena Spanish | 1373 | — |
Instruction Following Not comparable
Nova 2 Lite: 70.5 (#161), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1335 | — |
Long Context Not comparable
Nova 2 Lite: 40.6 (#150), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1335 | — |
Writing & Preference Not comparable
Nova 2 Lite: 53.9 (#154), phi-3-medium 14B: —
| Benchmark | Nova 2 Lite | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1362 | — |
| LMArena Creative Writing | 1291 | — |
| LMArena Multi-Turn | 1338 | — |
Frequently asked questions
Is Nova 2 Lite better than phi-3-medium 14B?
Nova 2 Lite is the stronger model overall, scoring 39.7 to 29.7 on the Noometry Index.
Is Nova 2 Lite or phi-3-medium 14B better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 36.8 in the Noometry coding category.
How many benchmarks do Nova 2 Lite and phi-3-medium 14B share?
0 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and phi-3-medium 14B has 13.