Model comparison
Gemma 2 27B vs Llama 3.1-405B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
MetaSummary
- They share 24 benchmarks with published results for both. Gemma 2 27B scores higher in 2 categories and Llama 3.1-405B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 19.0.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 49.8% for Llama 3.1-405B.
Side by side
| Gemma 2 27B | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.4 | 30.7 |
| Released | 2024-06-24 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 27B: 34.1 (#246), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1211 | 1291 |
| WeirdML | — | 21.4% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Llama 3.1-405B leads
Gemma 2 27B: 15.3 (#315), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1269 |
| DTBench | 48% | 61.4% |
| Epoch Capabilities Index | 122.08 | 128.75 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 38.2% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Llama 3.1-405B leads
Gemma 2 27B: 10.7 (#311), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 9.7% |
| LMArena Math | 1212 | 1281 |
| MATH Level 5 | 27.9% | 49.8% |
| Omni-MATH | — | 24.9% |
| LiveBench Math | 26.5% | — |
Knowledge Llama 3.1-405B leads
Gemma 2 27B: 19.0 (#280), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 36.5% | 50.9% |
| Confabulations | 27.1% | 17.6% |
| LMArena Expert | 1172 | 1243 |
| MMLU | 75.7% | 84.5% |
| MMLU-Pro | — | 72.3% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multilingual Llama 3.1-405B leads
Gemma 2 27B: 38.6 (#226), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1217 | 1248 |
| LMArena Chinese | 1221 | 1242 |
| LMArena French | 1247 | 1279 |
| LMArena German | 1209 | 1252 |
| LMArena Japanese | 1175 | 1208 |
| LMArena Korean | 1174 | 1184 |
| LMArena Russian | 1234 | 1265 |
| LMArena Spanish | 1228 | 1260 |
Instruction Following Llama 3.1-405B leads
Gemma 2 27B: 60.5 (#249), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1259 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
Gemma 2 27B: 37.3 (#218), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1231 | 1266 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Gemma 2 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1231 | 1284 |
| LMArena Creative Writing | 1241 | 1262 |
| LMArena Multi-Turn | 1224 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 3.1-405B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 29.4 on the Noometry Index.
Is Gemma 2 27B or Llama 3.1-405B better for coding?
They score almost the same on coding (34.1 vs 33.1); test both on your own repository before choosing.
How many benchmarks do Gemma 2 27B and Llama 3.1-405B share?
24 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 3.1-405B has 42.