Model comparison
Gemma 2 2b IT vs Phi 3 Mini 4k Instruct
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MicrosoftSummary
- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 2 2b IT leads 57.8 to 47.7.
Side by side
| Gemma 2 2b IT | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 33.1 | 27.9 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 2b IT leads
Gemma 2 2b IT: 32.3 (#273), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1112 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Gemma 2 2b IT leads
Gemma 2 2b IT: 21.4 (#224), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 32.6 (#212), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1135 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.9 (#231), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1096 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Gemma 2 2b IT leads
Gemma 2 2b IT: 32.3 (#257), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1121 | 1021 |
| LMArena Chinese | 1132 | 1021 |
| LMArena French | 1157 | 1076 |
| LMArena German | 1114 | 1044 |
| LMArena Japanese | 1083 | 935 |
| LMArena Korean | 1055 | 905 |
| LMArena Russian | 1118 | 1022 |
| LMArena Spanish | 1140 | 1085 |
Instruction Following Gemma 2 2b IT leads
Gemma 2 2b IT: 57.8 (#263), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1118 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Gemma 2 2b IT leads
Gemma 2 2b IT: 34.3 (#250), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1130 | 1044 |
Writing & Preference Gemma 2 2b IT leads
Gemma 2 2b IT: 36.5 (#263), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Gemma 2 2b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1156 | 1073 |
| LMArena Creative Writing | 1147 | 1037 |
| LMArena Multi-Turn | 1118 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemma 2 2b IT better than Phi 3 Mini 4k Instruct?
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 27.9 on the Noometry Index.
Is Gemma 2 2b IT or Phi 3 Mini 4k Instruct better for coding?
Gemma 2 2b IT scores higher on coding benchmarks: 32.3 versus 26.6 in the Noometry coding category.
How many benchmarks do Gemma 2 2b IT and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.