Model comparison
Gemma 2 2b IT vs Gemma 7B
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 30.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Gemma 2 2b IT scores higher in 8 categories and Gemma 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 2b IT leads 36.5 to 27.1.
Side by side
| Gemma 2 2b IT | Gemma 7B | |
|---|---|---|
| Provider | ||
| Noometry Index | 33.1 | 30.0 |
| Released | — | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 27 |
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), Gemma 7B: 30.5 (#294)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Coding | 1112 | 1048 |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |
Reasoning Gemma 2 2b IT leads
Gemma 2 2b IT: 21.4 (#224), Gemma 7B: 19.9 (#249)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1042 |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| Epoch Capabilities Index | — | 111.99 |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 32.6 (#212), Gemma 7B: 31.2 (#228)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Math | 1135 | 1066 |
| GSM8K | — | 46.4% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.9 (#231), Gemma 7B: 27.3 (#252)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Expert | 1096 | 1001 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual Gemma 2 2b IT leads
Gemma 2 2b IT: 32.3 (#257), Gemma 7B: 25.1 (#287)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1121 | 999 |
| LMArena Chinese | 1132 | 1035 |
| LMArena French | 1157 | 1025 |
| LMArena Russian | 1118 | 993 |
| LMArena German | 1114 | — |
| LMArena Japanese | 1083 | — |
| LMArena Korean | 1055 | — |
| LMArena Spanish | 1140 | — |
Instruction Following Gemma 2 2b IT leads
Gemma 2 2b IT: 57.8 (#263), Gemma 7B: 51.5 (#295)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1017 |
Long Context Gemma 2 2b IT leads
Gemma 2 2b IT: 34.3 (#250), Gemma 7B: 31.1 (#282)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1130 | 1022 |
Writing & Preference Gemma 2 2b IT leads
Gemma 2 2b IT: 36.5 (#263), Gemma 7B: 27.1 (#302)
| Benchmark | Gemma 2 2b IT | Gemma 7B |
|---|---|---|
| LMArena Text | 1156 | 1056 |
| LMArena Creative Writing | 1147 | 1024 |
| LMArena Multi-Turn | 1118 | 963 |
Frequently asked questions
Is Gemma 2 2b IT better than Gemma 7B?
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 30.0 on the Noometry Index.
Is Gemma 2 2b IT or Gemma 7B better for coding?
Gemma 2 2b IT scores higher on coding benchmarks: 32.3 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 2 2b IT and Gemma 7B share?
13 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Gemma 7B has 27.