Model comparison
Gemma 2 27B vs Phi 3 Mini 4k Instruct
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MicrosoftSummary
- They share 25 benchmarks with published results for both. Gemma 2 27B 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 writing & preference, where Gemma 2 27B leads 44.2 to 27.6.
- The biggest single-benchmark swing is LiveBench Language: 32.6% for Gemma 2 27B and 9.2% for Phi 3 Mini 4k Instruct.
Side by side
| Gemma 2 27B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.4 | 27.9 |
| Released | 2024-06-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 34.1 (#246), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 36% | 15.5% |
| LMArena Coding | 1211 | 1093 |
| BigCodeBench Instruct | 42.8% | — |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Gemma 2 27B leads
Gemma 2 27B: 15.3 (#315), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 28.1% | 26.8% |
| LMArena Hard Prompts | 1198 | 1072 |
| LiveBench Data Analysis | 47.9% | 34.7% |
| LiveBench | 38.2% | 22.4% |
| Chess Puzzles | — | 0% |
| DTBench | 48% | — |
| LMCA | 7.1% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 122.08 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Gemma 2 27B: 10.7 (#311), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 26.5% | 15.7% |
| LMArena Math | 1212 | 1111 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Gemma 2 27B: 19.0 (#280), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1172 | 1045 |
| MMLU | 75.7% | 68.8% |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Gemma 2 27B leads
Gemma 2 27B: 38.6 (#226), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1217 | 1021 |
| LMArena Chinese | 1221 | 1021 |
| LMArena French | 1247 | 1076 |
| LMArena German | 1209 | 1044 |
| LMArena Japanese | 1175 | 935 |
| LMArena Korean | 1174 | 905 |
| LMArena Russian | 1234 | 1022 |
| LMArena Spanish | 1228 | 1085 |
Instruction Following Gemma 2 27B leads
Gemma 2 27B: 60.5 (#249), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 39.1% |
| LMArena Instruction Following | 1206 | 1053 |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1231 | 1044 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemma 2 27B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1231 | 1073 |
| LMArena Creative Writing | 1241 | 1037 |
| LMArena Multi-Turn | 1224 | 1018 |
| LiveBench Language | 32.6% | 9.2% |
Frequently asked questions
Is Gemma 2 27B better than Phi 3 Mini 4k Instruct?
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.9 on the Noometry Index.
Is Gemma 2 27B or Phi 3 Mini 4k Instruct better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.