Model comparison
Gemma 2B vs Phi 3 Small 8k Instruct
Gemma 2B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.6 vs 29.3), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemma 2B scores higher in 3 categories and Phi 3 Small 8k Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Small 8k Instruct leads 31.1 to 24.0.
Side by side
| Gemma 2B | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 29.6 | 29.3 |
| Released | 2024-02-21 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Gemma 2B: 29.4 (#305), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1010 | 1101 |
| LiveBench Coding | — | 20.3% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Gemma 2B leads
Gemma 2B: 18.8 (#275), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 989 | 1100 |
| BIG-Bench Hard | 35.2% | 79.1% |
| HellaSwag | 71.4% | 77% |
| WinoGrande | 65.4% | 81.5% |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| Epoch Capabilities Index | 94.2 | — |
| LiveBench | — | 24% |
| PIQA | 77.3% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1009 | 1151 |
| LiveBench Math | — | 17.6% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | 90.7% |
| MMLU | 42.3% | 75.7% |
| TriviaQA | 53.2% | 58.1% |
| LMArena Expert | — | 1067 |
| BoolQ | 69.4% | — |
| OpenBookQA | — | 88% |
Multilingual Phi 3 Small 8k Instruct leads
Gemma 2B: 23.0 (#294), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 958 | 1058 |
| LMArena Chinese | 986 | 1061 |
| LMArena Russian | 937 | 1111 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Spanish | — | 1111 |
Instruction Following Phi 3 Small 8k Instruct leads
Gemma 2B: 48.5 (#302), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 970 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Phi 3 Small 8k Instruct leads
Gemma 2B: 29.9 (#291), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 981 | 1088 |
Writing & Preference Phi 3 Small 8k Instruct leads
Gemma 2B: 24.0 (#308), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Gemma 2B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1002 | 1110 |
| LMArena Creative Writing | 987 | 1083 |
| LMArena Multi-Turn | 945 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Gemma 2B better than Phi 3 Small 8k Instruct?
Gemma 2B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.6 vs 29.3), so choose on price, context window or the category you care about most.
Is Gemma 2B or Phi 3 Small 8k Instruct better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 27.9 in the Noometry coding category.
How many benchmarks do Gemma 2B and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Phi 3 Small 8k Instruct has 32.