Model comparison
Gemma 7B vs phi-3-medium 14B
Gemma 7B and phi-3-medium 14B score almost the same on the Noometry Index (30.0 vs 29.7), so choose on price, context window or the category you care about most.
Last verified . 9 shared benchmarks.
Google
MicrosoftSummary
- They share 9 benchmarks with published results for both. Gemma 7B scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 7B leads 27.3 to 9.1.
Side by side
| Gemma 7B | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 30.0 | 29.7 |
| Released | 2024-02-21 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Gemma 7B: 30.5 (#294), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1048 | — |
| BigCodeBench Complete | — | 48.7% |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Not comparable
Gemma 7B: 19.9 (#249), phi-3-medium 14B: —
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| Adversarial NLI | 48.7% | 55.8% |
| BIG-Bench Hard | 55.1% | 81.4% |
| Epoch Capabilities Index | 111.99 | 121.23 |
| HellaSwag | 82.2% | 82.4% |
| WinoGrande | 79% | 81.5% |
| LMArena Hard Prompts | 1042 | — |
| PIQA | 81.2% | — |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1066 | — |
| MATH Level 5 | — | 17.6% |
| GSM8K | 46.4% | — |
Knowledge Gemma 7B leads
Gemma 7B: 27.3 (#252), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 78.3% | 91.6% |
| MMLU | 66.1% | 78% |
| OpenBookQA | 78.6% | 87.4% |
| TriviaQA | 72.3% | 73.9% |
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1001 | — |
| BoolQ | 83.2% | — |
Multilingual Not comparable
Gemma 7B: 25.1 (#287), phi-3-medium 14B: —
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 999 | — |
| LMArena Chinese | 1035 | — |
| LMArena French | 1025 | — |
| LMArena Russian | 993 | — |
Instruction Following Not comparable
Gemma 7B: 51.5 (#295), phi-3-medium 14B: —
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1017 | — |
Long Context Not comparable
Gemma 7B: 31.1 (#282), phi-3-medium 14B: —
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1022 | — |
Writing & Preference Not comparable
Gemma 7B: 27.1 (#302), phi-3-medium 14B: —
| Benchmark | Gemma 7B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1056 | — |
| LMArena Creative Writing | 1024 | — |
| LMArena Multi-Turn | 963 | — |
Frequently asked questions
Is Gemma 7B better than phi-3-medium 14B?
Gemma 7B and phi-3-medium 14B score almost the same on the Noometry Index (30.0 vs 29.7), so choose on price, context window or the category you care about most.
Is Gemma 7B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and phi-3-medium 14B share?
9 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and phi-3-medium 14B has 13.