Model comparison
Gemma 3 27B vs phi-3-medium 14B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
Google
MicrosoftSummary
- They share 3 benchmarks with published results for both. Gemma 3 27B 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 27B leads 25.5 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 17.6% for phi-3-medium 14B.
Side by side
| Gemma 3 27B | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 30.8 | 29.7 |
| Released | 2025-03-11 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Gemma 3 27B: 22.5 (#334), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 39.9% | — |
| LMArena Coding | 1322 | — |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Not comparable
Gemma 3 27B: 16.7 (#301), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 130.04 | 121.23 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LMArena Hard Prompts | 1340 | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| LiveBench | 50% | — |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Gemma 3 27B: 25.9 (#265), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 74% | 17.6% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| LMArena Math | 1312 | — |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 47.7% | 27.6% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1304 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Gemma 3 27B: 46.9 (#155), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1334 | — |
| LMArena Chinese | 1346 | — |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Russian | 1349 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Not comparable
Gemma 3 27B: 70.6 (#160), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 74.9% | — |
| LMArena Instruction Following | 1321 | — |
Long Context Not comparable
Gemma 3 27B: 27.6 (#293), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 33.3% | — |
| LMArena Longer Query | 1333 | — |
Writing & Preference Not comparable
Gemma 3 27B: 52.5 (#168), phi-3-medium 14B: —
| Benchmark | Gemma 3 27B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1358 | — |
| LMArena Creative Writing | 1346 | — |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LMArena Multi-Turn | 1345 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than phi-3-medium 14B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.7 on the Noometry Index.
Is Gemma 3 27B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and phi-3-medium 14B share?
3 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and phi-3-medium 14B has 13.