Model comparison
Gemma 7B vs Llama 3-70B
Gemma 7B is the stronger model overall, scoring 30.0 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
MetaSummary
- They share 18 benchmarks with published results for both. Gemma 7B scores higher in 3 categories and Llama 3-70B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 31.2 to 12.8.
Side by side
| Gemma 7B | Llama 3-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.0 | 28.8 |
| Released | 2024-02-21 | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Gemma 7B: 30.5 (#294), Llama 3-70B: 35.8 (#218)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1048 | 1206 |
| HumanEval+ | 28.7% | 72% |
| MBPP+ | 43.4% | 69% |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
Agentic & Tool Use Not comparable
Gemma 7B: —, Llama 3-70B: 21.1 (#139)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Gemma 7B leads
Gemma 7B: 19.9 (#249), Llama 3-70B: 18.0 (#288)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1195 |
| Epoch Capabilities Index | 111.99 | 122.93 |
| WinoGrande | 79% | 83.5% |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| ForecastBench | — | 57.1 |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), Llama 3-70B: 12.8 (#305)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Math | 1066 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
| GSM8K | 46.4% | — |
Knowledge Gemma 7B leads
Gemma 7B: 27.3 (#252), Llama 3-70B: 20.8 (#277)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1001 | 1149 |
| MMLU | 66.1% | 79.3% |
| GPQA Diamond | — | 40.6% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Llama 3-70B leads
Gemma 7B: 25.1 (#287), Llama 3-70B: 33.6 (#251)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 999 | 1142 |
| LMArena Chinese | 1035 | 1114 |
| LMArena French | 1025 | 1232 |
| LMArena Russian | 993 | 1159 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Spanish | — | 1241 |
Instruction Following Llama 3-70B leads
Gemma 7B: 51.5 (#295), Llama 3-70B: 62.5 (#238)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1194 |
Long Context Llama 3-70B leads
Gemma 7B: 31.1 (#282), Llama 3-70B: 35.6 (#240)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1022 | 1174 |
Writing & Preference Llama 3-70B leads
Gemma 7B: 27.1 (#302), Llama 3-70B: 42.8 (#231)
| Benchmark | Gemma 7B | Llama 3-70B |
|---|---|---|
| LMArena Text | 1056 | 1221 |
| LMArena Creative Writing | 1024 | 1210 |
| LMArena Multi-Turn | 963 | 1223 |
Frequently asked questions
Is Gemma 7B better than Llama 3-70B?
Gemma 7B is the stronger model overall, scoring 30.0 to 28.8 on the Noometry Index.
Is Gemma 7B or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Llama 3-70B share?
18 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Llama 3-70B has 31.