Model comparison
Gemma 7B vs Llama 3.1-405B
Gemma 7B and Llama 3.1-405B score almost the same on the Noometry Index (30.0 vs 30.7), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Google
MetaSummary
- They share 21 benchmarks with published results for both. Gemma 7B scores higher in 2 categories and Llama 3.1-405B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-405B leads 40.7 to 25.1.
Side by side
| Gemma 7B | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.0 | 30.7 |
| Released | 2024-02-21 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Gemma 7B: 30.5 (#294), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1048 | 1291 |
| WeirdML | — | 21.4% |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Agentic & Tool Use Not comparable
Gemma 7B: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Gemma 7B leads
Gemma 7B: 19.9 (#249), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1269 |
| BIG-Bench Hard | 55.1% | 82.9% |
| Epoch Capabilities Index | 111.99 | 128.75 |
| HellaSwag | 82.2% | 89.2% |
| PIQA | 81.2% | 85.9% |
| WinoGrande | 79% | 89.2% |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| DTBench | — | 61.4% |
| Adversarial NLI | 48.7% | — |
| ForecastBench | — | 59.9 |
Math Gemma 7B leads
Gemma 7B: 31.2 (#228), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1066 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
| GSM8K | 46.4% | — |
Knowledge Llama 3.1-405B leads
Gemma 7B: 27.3 (#252), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1001 | 1243 |
| ARC (AI2) Challenge | 78.3% | 95.3% |
| MMLU | 66.1% | 84.5% |
| TriviaQA | 72.3% | 82.7% |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| BoolQ | 83.2% | — |
| OpenBookQA | 78.6% | — |
Multilingual Llama 3.1-405B leads
Gemma 7B: 25.1 (#287), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 999 | 1248 |
| LMArena Chinese | 1035 | 1242 |
| LMArena French | 1025 | 1279 |
| LMArena Russian | 993 | 1265 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1260 |
Instruction Following Llama 3.1-405B leads
Gemma 7B: 51.5 (#295), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1259 |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
Gemma 7B: 31.1 (#282), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1022 | 1266 |
Writing & Preference Llama 3.1-405B leads
Gemma 7B: 27.1 (#302), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Gemma 7B | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1056 | 1284 |
| LMArena Creative Writing | 1024 | 1262 |
| LMArena Multi-Turn | 963 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Gemma 7B better than Llama 3.1-405B?
Gemma 7B and Llama 3.1-405B score almost the same on the Noometry Index (30.0 vs 30.7), so choose on price, context window or the category you care about most.
Is Gemma 7B or Llama 3.1-405B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Llama 3.1-405B share?
21 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Llama 3.1-405B has 42.