Model comparison
Gemma 3 27B vs Phi 3 Mini 128k Instruct
Gemma 3 27B is the stronger model overall, scoring 30.5 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemma 3 27B scores higher in 3 categories and Phi 3 Mini 128k Instruct in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.7 to 27.3.
Side by side
| Gemma 3 27B | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 30.5 | 29.1 |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 128k Instruct leads
Gemma 3 27B: 22.1 (#329), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1322 | 1040 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| BigCodeBench Instruct | — | 29.6% |
| LiveBench Coding | 39.9% | — |
| BigCodeBench Complete | — | 40.6% |
Agentic & Tool Use Not comparable
Gemma 3 27B: 24.9 (#105), Phi 3 Mini 128k Instruct: —
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Gemma 3 27B: 16.3 (#297), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1028 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Phi 3 Mini 128k Instruct leads
Gemma 3 27B: 24.4 (#261), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1312 | 1089 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Too close to call
Gemma 3 27B: 25.4 (#256), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1303 | 984 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.0 (#94), Phi 3 Mini 128k Instruct: —
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 47.0 (#150), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1334 | 1000 |
| LMArena Chinese | 1347 | 1016 |
| LMArena French | 1368 | 1038 |
| LMArena German | 1362 | 1006 |
| LMArena Japanese | 1287 | 899 |
| LMArena Korean | 1308 | 856 |
| LMArena Russian | 1349 | 1004 |
| LMArena Spanish | 1348 | 1058 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.8 (#155), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1321 | 1023 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Phi 3 Mini 128k Instruct leads
Gemma 3 27B: 27.6 (#288), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1333 | 996 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.7 (#161), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | Gemma 3 27B | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1358 | 1050 |
| LMArena Creative Writing | 1346 | 1024 |
| LMArena Multi-Turn | 1344 | 989 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Phi 3 Mini 128k Instruct?
Gemma 3 27B is the stronger model overall, scoring 30.5 to 29.1 on the Noometry Index.
Is Gemma 3 27B or Phi 3 Mini 128k Instruct better for coding?
Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.3 versus 22.1 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Phi 3 Mini 128k Instruct share?
17 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.