Model comparison
Gemma 3 12B vs Phi-3.5-MoE
Gemma 3 12B has enough public results to be ranked (#262); Phi-3.5-MoE does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
MicrosoftSide by side
| Gemma 3 12B | Phi-3.5-MoE | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.1 | — |
| Released | 2025-03-12 | 2024-08-17 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 12B: 31.7 (#280), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| SciCode | 17.4% | — |
| LMArena Coding | 1281 | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Not comparable
Gemma 3 12B: 15.7 (#313), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
| PIQA | — | 88.6% |
Math Not comparable
Gemma 3 12B: 22.3 (#279), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LMArena Math | 1307 | — |
| GSM8K | — | 88.7% |
Knowledge Not comparable
Gemma 3 12B: 26.5 (#257), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
| BoolQ | — | 84.6% |
Multimodal Not comparable
Gemma 3 12B: —, Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Not comparable
Gemma 3 12B: 45.7 (#165), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Not comparable
Gemma 3 12B: 68.6 (#186), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| LMArena Instruction Following | 1299 | — |
Long Context Not comparable
Gemma 3 12B: 40.0 (#162), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| LMArena Longer Query | 1317 | — |
Writing & Preference Not comparable
Gemma 3 12B: 47.5 (#209), Phi-3.5-MoE: —
| Benchmark | Gemma 3 12B | Phi-3.5-MoE |
|---|---|---|
| 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-3.5-MoE?
Gemma 3 12B has enough public results to be ranked (#262); Phi-3.5-MoE does not yet, so treat this comparison as directional.
How many benchmarks do Gemma 3 12B and Phi-3.5-MoE share?
0 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Phi-3.5-MoE has 3.