Model comparison
Gemma 1.1 7b IT vs Phi 3 Mini 4k Instruct
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 27.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
MicrosoftSummary
- They share 19 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 7 categories and Phi 3 Mini 4k Instruct in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 1.1 7b IT leads 54.3 to 48.0.
Side by side
| Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Microsoft | |
| Noometry Index | 30.7 | 27.4 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 31.0 (#279), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1084 | 1093 |
| HumanEval+ | 35.4% | 59.1% |
| MBPP+ | 45% | 54.2% |
| LiveBench Coding | — | 15.5% |
Reasoning Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 19.6 (#235), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1071 | 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 1.1 7b IT leads
Gemma 1.1 7b IT: 29.5 (#217), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1107 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Too close to call
Gemma 1.1 7b IT: 27.8 (#242), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1039 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 28.3 (#268), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1052 | 1021 |
| LMArena Chinese | 1060 | 1021 |
| LMArena French | 1064 | 1075 |
| LMArena German | 1054 | 1044 |
| LMArena Japanese | 971 | 935 |
| LMArena Korean | 988 | 905 |
| LMArena Russian | 1046 | 1022 |
| LMArena Spanish | 1049 | 1084 |
Instruction Following Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 54.3 (#278), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1057 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Too close to call
Gemma 1.1 7b IT: 32.0 (#267), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1056 | 1044 |
Writing & Preference Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 30.6 (#283), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Gemma 1.1 7b IT | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1094 | 1073 |
| LMArena Creative Writing | 1059 | 1037 |
| LMArena Multi-Turn | 1040 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Gemma 1.1 7b IT better than Phi 3 Mini 4k Instruct?
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 27.4 on the Noometry Index.
Is Gemma 1.1 7b IT or Phi 3 Mini 4k Instruct better for coding?
Gemma 1.1 7b IT scores higher on coding benchmarks: 31.0 versus 26.1 in the Noometry coding category.
How many benchmarks do Gemma 1.1 7b IT and Phi 3 Mini 4k Instruct share?
19 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.