Model comparison
Nova 2 Lite vs Phi-3.5-mini
Nova 2 Lite has enough public results to be ranked (#161); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where Nova 2 Lite leads 40.1 to 34.0.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Nova 2 Lite | Phi-3.5-mini | |
|---|---|---|
| Provider | Amazon | Microsoft |
| Noometry Index | 39.0 | 36.4 |
| Released | 2025-12-01 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 19 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Nova 2 Lite: 40.1 (#131), Phi-3.5-mini: 34.0 (#231)
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1386 | — |
| BigCodeBench Complete | — | 38.5% |
Agentic & Tool Use Not comparable
Nova 2 Lite: 23.9 (#114), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Not comparable
Nova 2 Lite: 26.4 (#120), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Hard Prompts | 1364 | — |
| PIQA | — | 81% |
Math Not comparable
Nova 2 Lite: 34.8 (#154), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Math | 1359 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Nova 2 Lite: 42.5 (#88), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | — |
| LMArena Expert | 1360 | — |
| BoolQ | — | 78% |
Multilingual Not comparable
Nova 2 Lite: 47.3 (#148), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1337 | — |
| LMArena Chinese | 1364 | — |
| LMArena French | 1381 | — |
| LMArena German | 1343 | — |
| LMArena Japanese | 1273 | — |
| LMArena Korean | 1284 | — |
| LMArena Russian | 1343 | — |
| LMArena Spanish | 1372 | — |
Instruction Following Not comparable
Nova 2 Lite: 70.7 (#156), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1335 | — |
Long Context Not comparable
Nova 2 Lite: 40.6 (#145), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1335 | — |
Writing & Preference Not comparable
Nova 2 Lite: 54.1 (#150), Phi-3.5-mini: —
| Benchmark | Nova 2 Lite | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1362 | — |
| LMArena Creative Writing | 1291 | — |
| LMArena Multi-Turn | 1338 | — |
Frequently asked questions
Is Nova 2 Lite better than Phi-3.5-mini?
Nova 2 Lite has enough public results to be ranked (#161); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Nova 2 Lite or Phi-3.5-mini better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 34.0 in the Noometry coding category.
How many benchmarks do Nova 2 Lite and Phi-3.5-mini share?
0 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Phi-3.5-mini has 5.