Model comparison
Gemma 2 9B vs Phi 3 Mini 4k Instruct
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MicrosoftSummary
- They share 25 benchmarks with published results for both. Gemma 2 9B 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 knowledge, where Phi 3 Mini 4k Instruct leads 28.5 to 9.7.
- The biggest single-benchmark swing is LiveBench Language: 25.5% for Gemma 2 9B and 9.2% for Phi 3 Mini 4k Instruct.
Side by side
| Gemma 2 9B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 25.9 | 27.9 |
| Released | 2024-06-24 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemma 2 9B: 29.4 (#304), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 22.5% | 15.5% |
| LMArena Coding | 1173 | 1093 |
| BigCodeBench Instruct | 34.7% | — |
| BigCodeBench Complete | 40.6% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Gemma 2 9B leads
Gemma 2 9B: 15.9 (#309), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 15.2% | 26.8% |
| LMArena Hard Prompts | 1171 | 1072 |
| LiveBench Data Analysis | 36.4% | 34.7% |
| LiveBench | 28.7% | 22.4% |
| Chess Puzzles | — | 0% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 119.83 | — |
| HellaSwag | — | 76.7% |
| PIQA | 83.7% | — |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
Gemma 2 9B: 9.9 (#318), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 19.8% | 15.7% |
| LMArena Math | 1183 | 1111 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Gemma 2 9B: 9.7 (#305), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1147 | 1045 |
| MMLU | 72.1% | 68.8% |
| GPQA Diamond | 27.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| BoolQ | 85.7% | — |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1188 | 1021 |
| LMArena Chinese | 1185 | 1021 |
| LMArena French | 1190 | 1076 |
| LMArena German | 1186 | 1044 |
| LMArena Japanese | 1144 | 935 |
| LMArena Korean | 1137 | 905 |
| LMArena Russian | 1200 | 1022 |
| LMArena Spanish | 1200 | 1085 |
Instruction Following Gemma 2 9B leads
Gemma 2 9B: 57.6 (#269), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 39.1% |
| LMArena Instruction Following | 1178 | 1053 |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1197 | 1044 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemma 2 9B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1207 | 1073 |
| LMArena Creative Writing | 1206 | 1037 |
| LMArena Multi-Turn | 1193 | 1018 |
| LiveBench Language | 25.5% | 9.2% |
| EQ-Bench Creative Writing | 841 | — |
Frequently asked questions
Is Gemma 2 9B better than Phi 3 Mini 4k Instruct?
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Phi 3 Mini 4k Instruct better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.