Model comparison
Gemma 2B vs phi-3-medium 14B
Gemma 2B and phi-3-medium 14B score almost the same on the Noometry Index (29.6 vs 29.7), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Google
MicrosoftSummary
- They share 7 benchmarks with published results for both. Gemma 2B scores higher in 1 category and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where phi-3-medium 14B leads 36.8 to 29.4.
Side by side
| Gemma 2B | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.6 | 29.7 |
| Released | 2024-02-21 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Gemma 2B: 29.4 (#305), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1010 | — |
| BigCodeBench Complete | — | 48.7% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Not comparable
Gemma 2B: 18.8 (#275), phi-3-medium 14B: —
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| BIG-Bench Hard | 35.2% | 81.4% |
| Epoch Capabilities Index | 94.2 | 121.23 |
| HellaSwag | 71.4% | 82.4% |
| WinoGrande | 65.4% | 81.5% |
| LMArena Hard Prompts | 989 | — |
| Adversarial NLI | — | 55.8% |
| PIQA | 77.3% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1009 | — |
| MATH Level 5 | — | 17.6% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, phi-3-medium 14B: 9.1 (#306)
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 91.6% |
| MMLU | 42.3% | 78% |
| TriviaQA | 53.2% | 73.9% |
| GPQA Diamond | — | 27.6% |
| BoolQ | 69.4% | — |
| OpenBookQA | — | 87.4% |
Multilingual Not comparable
Gemma 2B: 23.0 (#294), phi-3-medium 14B: —
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 958 | — |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |
Instruction Following Not comparable
Gemma 2B: 48.5 (#302), phi-3-medium 14B: —
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 970 | — |
Long Context Not comparable
Gemma 2B: 29.9 (#291), phi-3-medium 14B: —
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 981 | — |
Writing & Preference Not comparable
Gemma 2B: 24.0 (#308), phi-3-medium 14B: —
| Benchmark | Gemma 2B | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1002 | — |
| LMArena Creative Writing | 987 | — |
| LMArena Multi-Turn | 945 | — |
Frequently asked questions
Is Gemma 2B better than phi-3-medium 14B?
Gemma 2B and phi-3-medium 14B score almost the same on the Noometry Index (29.6 vs 29.7), so choose on price, context window or the category you care about most.
Is Gemma 2B or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and phi-3-medium 14B share?
7 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and phi-3-medium 14B has 13.