Model comparison
Gemma 2 2b IT vs phi-3-medium 14B
Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Google
MicrosoftSummary
- The widest gap is in knowledge, where Gemma 2 2b IT leads 29.3 to 9.1.
Side by side
| Gemma 2 2b IT | phi-3-medium 14B | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 32.5 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Gemma 2 2b IT: 31.8 (#268), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1112 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Gemma 2 2b IT: 20.5 (#219), phi-3-medium 14B: —
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1113 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 30.1 (#212), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1135 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.3 (#229), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1096 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Gemma 2 2b IT: 32.5 (#252), phi-3-medium 14B: —
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1121 | — |
| LMArena Chinese | 1132 | — |
| LMArena French | 1156 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 1083 | — |
| LMArena Korean | 1055 | — |
| LMArena Russian | 1118 | — |
| LMArena Spanish | 1140 | — |
Instruction Following Not comparable
Gemma 2 2b IT: 58.1 (#258), phi-3-medium 14B: —
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1118 | — |
Long Context Not comparable
Gemma 2 2b IT: 34.2 (#245), phi-3-medium 14B: —
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1130 | — |
Writing & Preference Not comparable
Gemma 2 2b IT: 36.6 (#258), phi-3-medium 14B: —
| Benchmark | Gemma 2 2b IT | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1156 | — |
| LMArena Creative Writing | 1147 | — |
| LMArena Multi-Turn | 1118 | — |
Frequently asked questions
Is Gemma 2 2b IT better than phi-3-medium 14B?
Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 29.1 on the Noometry Index.
Is Gemma 2 2b IT or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 31.8 in the Noometry coding category.
How many benchmarks do Gemma 2 2b IT and phi-3-medium 14B share?
0 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and phi-3-medium 14B has 13.