Model comparison
Gemma 1.1 7b IT vs Gemma 7B
Gemma 1.1 7b IT is the stronger model overall, scoring 31.3 to 30.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
GoogleSummary
- They share 15 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 8 categories and Gemma 7B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 1.1 7b IT leads 30.4 to 27.1.
Side by side
| Gemma 1.1 7b IT | Gemma 7B | |
|---|---|---|
| Provider | ||
| Noometry Index | 31.3 | 30.0 |
| Released | — | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 27 |
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: 31.5 (#284), Gemma 7B: 30.5 (#294)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Coding | 1084 | 1048 |
| HumanEval+ | 35.4% | 28.7% |
| MBPP+ | 45% | 43.4% |
Reasoning Too close to call
Gemma 1.1 7b IT: 20.5 (#238), Gemma 7B: 19.9 (#249)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1042 |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| Epoch Capabilities Index | — | 111.99 |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Too close to call
Gemma 1.1 7b IT: 32.0 (#220), Gemma 7B: 31.2 (#228)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Math | 1107 | 1066 |
| GSM8K | — | 46.4% |
Knowledge Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 28.3 (#247), Gemma 7B: 27.3 (#252)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Expert | 1039 | 1001 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| MMLU | — | 66.1% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 28.1 (#273), Gemma 7B: 25.1 (#287)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1052 | 999 |
| LMArena Chinese | 1061 | 1035 |
| LMArena French | 1065 | 1025 |
| LMArena Russian | 1046 | 993 |
| LMArena German | 1054 | — |
| LMArena Japanese | 971 | — |
| LMArena Korean | 988 | — |
| LMArena Spanish | 1049 | — |
Instruction Following Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 54.0 (#283), Gemma 7B: 51.5 (#295)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1057 | 1017 |
Long Context Too close to call
Gemma 1.1 7b IT: 32.1 (#272), Gemma 7B: 31.1 (#282)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1056 | 1022 |
Writing & Preference Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 30.4 (#288), Gemma 7B: 27.1 (#302)
| Benchmark | Gemma 1.1 7b IT | Gemma 7B |
|---|---|---|
| LMArena Text | 1094 | 1056 |
| LMArena Creative Writing | 1060 | 1024 |
| LMArena Multi-Turn | 1040 | 963 |
Frequently asked questions
Is Gemma 1.1 7b IT better than Gemma 7B?
Gemma 1.1 7b IT is the stronger model overall, scoring 31.3 to 30.0 on the Noometry Index.
Is Gemma 1.1 7b IT or Gemma 7B better for coding?
Gemma 1.1 7b IT scores higher on coding benchmarks: 31.5 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 1.1 7b IT and Gemma 7B share?
15 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Gemma 7B has 27.