Model comparison
Gemma 3 4B vs phi-3-medium 14B
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 28.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
Google
MicrosoftSummary
- They share 2 benchmarks with published results for both. Gemma 3 4B scores higher in 1 category and phi-3-medium 14B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 27.3 to 16.8.
Side by side
| Gemma 3 4B | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 28.1 | 29.7 |
| Released | 2025-03-12 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 4B: 35.9 (#215), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1230 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Not comparable
Gemma 3 4B: 13.2 (#335), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 116.02 | 121.23 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Gemma 3 4B: 16.8 (#292), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Gemma 3 4B leads
Gemma 3 4B: 11.8 (#299), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 23.2% | 27.6% |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), phi-3-medium 14B: —
| Benchmark | Gemma 3 4B | phi-3-medium 14B |
|---|---|---|
| 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-3-medium 14B?
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 28.1 on the Noometry Index.
Is Gemma 3 4B or phi-3-medium 14B better for coding?
They score almost the same on coding (35.9 vs 36.8); test both on your own repository before choosing.
How many benchmarks do Gemma 3 4B and phi-3-medium 14B share?
2 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and phi-3-medium 14B has 13.