Model comparison
Gemma 3 4B vs Phi-1.5
Gemma 3 4B has enough public results to be ranked (#326); Phi-1.5 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Google
MicrosoftSummary
- They share 1 benchmark with published results for both.
Side by side
| Gemma 3 4B | Phi-1.5 | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 28.1 | — |
| Released | 2025-03-12 | 2023-09-11 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 4B: 35.9 (#215), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Not comparable
Gemma 3 4B: 13.2 (#335), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| Epoch Capabilities Index | 116.02 | 91.53 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| HellaSwag | — | 47.6% |
| WinoGrande | — | 73.4% |
Math Not comparable
Gemma 3 4B: 16.8 (#292), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 44.4% |
| BoolQ | — | 75.8% |
| MMLU | — | 37.6% |
| OpenBookQA | — | 37.2% |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), Phi-1.5: —
| Benchmark | Gemma 3 4B | Phi-1.5 |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1271 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |
Frequently asked questions
Is Gemma 3 4B better than Phi-1.5?
Gemma 3 4B has enough public results to be ranked (#326); Phi-1.5 does not yet, so treat this comparison as directional.
How many benchmarks do Gemma 3 4B and Phi-1.5 share?
1 benchmark has published results for both models. Gemma 3 4B has 22 scored results on Noometry and Phi-1.5 has 7.