Model comparison
Gemma 2B vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
MicrosoftSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Phi 3 Medium 4k Instruct in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Medium 4k Instruct leads 34.3 to 24.1.
Side by side
| Gemma 2B | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.1 | 32.4 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Medium 4k Instruct leads
Gemma 2B: 28.9 (#300), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1010 | 1130 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Phi 3 Medium 4k Instruct leads
Gemma 2B: 17.9 (#275), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 989 | 1127 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 93.57 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Phi 3 Medium 4k Instruct leads
Gemma 2B: 27.6 (#237), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1009 | 1173 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1108 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Phi 3 Medium 4k Instruct leads
Gemma 2B: 23.1 (#289), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 958 | 1094 |
| LMArena Chinese | 986 | 1108 |
| LMArena Russian | 937 | 1145 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |
Instruction Following Phi 3 Medium 4k Instruct leads
Gemma 2B: 48.8 (#297), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 971 | 1114 |
Long Context Phi 3 Medium 4k Instruct leads
Gemma 2B: 29.9 (#286), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 981 | 1120 |
Writing & Preference Phi 3 Medium 4k Instruct leads
Gemma 2B: 24.1 (#303), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Gemma 2B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1002 | 1138 |
| LMArena Creative Writing | 986 | 1106 |
| LMArena Multi-Turn | 945 | 1088 |
Frequently asked questions
Is Gemma 2B better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.1 on the Noometry Index.
Is Gemma 2B or Phi 3 Medium 4k Instruct better for coding?
Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 28.9 in the Noometry coding category.
How many benchmarks do Gemma 2B and Phi 3 Medium 4k Instruct share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.