Model comparison
Gemma 3 12B vs Phi 3 Mini 4k Instruct
Gemma 3 12B is the stronger model overall, scoring 32.1 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
MicrosoftSummary
- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 12B leads 68.6 to 47.7.
Side by side
| Gemma 3 12B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.1 | 27.9 |
| 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 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Gemma 3 12B: 31.7 (#280), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1093 |
| SciCode | 17.4% | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Phi 3 Mini 4k Instruct: —
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Gemma 3 12B leads
Gemma 3 12B: 15.7 (#313), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1309 | 1072 |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 48.8% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 4.5% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 123.5 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Gemma 3 12B: 22.3 (#279), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1307 | 1111 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LiveBench Math | — | 15.7% |
Knowledge Phi 3 Mini 4k Instruct leads
Gemma 3 12B: 26.5 (#257), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1248 | 1045 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
Gemma 3 12B: —, Phi 3 Mini 4k Instruct: —
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1021 |
| LMArena German | 1370 | 1044 |
| LMArena Russian | 1335 | 1022 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1085 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 1044 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemma 3 12B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1334 | 1073 |
| LMArena Creative Writing | 1331 | 1037 |
| LMArena Multi-Turn | 1334 | 1018 |
| EQ-Bench Creative Writing | 1126 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemma 3 12B better than Phi 3 Mini 4k Instruct?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 27.9 on the Noometry Index.
Is Gemma 3 12B or Phi 3 Mini 4k Instruct better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Phi 3 Mini 4k Instruct share?
13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.