Model comparison
Gemma 3 12B vs phi-3-medium 14B
Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
Google
MicrosoftSummary
- They share 2 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 27.6% for phi-3-medium 14B.
Side by side
| Gemma 3 12B | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.1 | 29.7 |
| Released | 2025-03-12 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Gemma 3 12B: 31.7 (#280), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1281 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Not comparable
Gemma 3 12B: 15.7 (#313), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 123.5 | 121.23 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Gemma 3 12B: 22.3 (#279), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LMArena Math | 1307 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Gemma 3 12B leads
Gemma 3 12B: 26.5 (#257), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 39.5% | 27.6% |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Gemma 3 12B: —, phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Not comparable
Gemma 3 12B: 45.7 (#165), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Not comparable
Gemma 3 12B: 68.6 (#186), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1299 | — |
Long Context Not comparable
Gemma 3 12B: 40.0 (#162), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1317 | — |
Writing & Preference Not comparable
Gemma 3 12B: 47.5 (#209), phi-3-medium 14B: —
| Benchmark | Gemma 3 12B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| LMArena Multi-Turn | 1334 | — |
Frequently asked questions
Is Gemma 3 12B better than phi-3-medium 14B?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 29.7 on the Noometry Index.
Is Gemma 3 12B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 31.7 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and phi-3-medium 14B share?
2 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and phi-3-medium 14B has 13.