Model comparison
Gemma 2 27B vs Phi-3.5-mini
Gemma 2 27B has enough public results to be ranked (#302); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Google
MicrosoftSummary
- They share 2 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Phi-3.5-mini in 1 category, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.5% for Gemma 2 27B and 38.5% for Phi-3.5-mini.
Side by side
| Gemma 2 27B | Phi-3.5-mini | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.2 | 36.4 |
| Released | 2024-06-24 | 2024-08-16 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 27B: 33.5 (#243), Phi-3.5-mini: 34.0 (#231)
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 32.8% |
| BigCodeBench Complete | 52.5% | 38.5% |
| LiveBench Coding | 36% | — |
| LMArena Coding | 1211 | — |
Reasoning Not comparable
Gemma 2 27B: 14.8 (#313), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1199 | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.06 | — |
| LiveBench | 38.2% | — |
| PIQA | — | 81% |
Math Not comparable
Gemma 2 27B: 10.0 (#306), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| LMArena Math | 1212 | — |
| MATH Level 5 | 27.9% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Gemma 2 27B: 18.9 (#275), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| LMArena Expert | 1172 | — |
| BoolQ | — | 78% |
| MMLU | 75.7% | — |
Multilingual Not comparable
Gemma 2 27B: 38.8 (#221), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1217 | — |
| LMArena Chinese | 1221 | — |
| LMArena French | 1246 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1228 | — |
Instruction Following Not comparable
Gemma 2 27B: 60.7 (#244), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| LiveBench Instruction Following | 58.1% | — |
| LMArena Instruction Following | 1206 | — |
Long Context Not comparable
Gemma 2 27B: 37.3 (#213), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1231 | — |
Writing & Preference Not comparable
Gemma 2 27B: 44.4 (#220), Phi-3.5-mini: —
| Benchmark | Gemma 2 27B | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1231 | — |
| LMArena Creative Writing | 1241 | — |
| LMArena Multi-Turn | 1224 | — |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Phi-3.5-mini?
Gemma 2 27B has enough public results to be ranked (#302); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Gemma 2 27B or Phi-3.5-mini better for coding?
They score almost the same on coding (33.5 vs 34.0); test both on your own repository before choosing.
How many benchmarks do Gemma 2 27B and Phi-3.5-mini share?
2 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Phi-3.5-mini has 5.