Model comparison
Gemma 2 27B vs Llama 3.1-70B
Gemma 2 27B and Llama 3.1-70B score almost the same on the Noometry Index (29.4 vs 29.6), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
Google
MetaSummary
- They share 26 benchmarks with published results for both. Gemma 2 27B scores higher in 2 categories and Llama 3.1-70B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.2 to 35.4.
- The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 60% for Llama 3.1-70B.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Llama 3.1-70B accepts more context: 128K tokens versus 8K.
Side by side
| Gemma 2 27B | Llama 3.1-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.4 | 29.6 |
| Released | 2024-06-24 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 8K | 128K |
| Max output | 2K | 4K |
| Input $ / M tokens | $0.65 | $0.40 |
| Output $ / M tokens | $0.65 | $0.40 |
| Results tracked | 34 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 34.1 (#246), Llama 3.1-70B: 30.3 (#296)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 46.1% |
| LMArena Coding | 1211 | 1260 |
| BigCodeBench Complete | 52.5% | 54.8% |
| WeirdML | — | 9% |
| LiveBench Coding | 36% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Llama 3.1-70B: 25.1 (#112)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Llama 3.1-70B leads
Gemma 2 27B: 15.3 (#315), Llama 3.1-70B: 21.6 (#220)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1241 |
| DTBench | 48% | 60% |
| LMCA | 7.1% | 14.8% |
| Epoch Capabilities Index | 122.08 | 125.92 |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| LiveBench | 38.2% | — |
Math Llama 3.1-70B leads
Gemma 2 27B: 10.7 (#311), Llama 3.1-70B: 13.5 (#304)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 3.6% |
| LMArena Math | 1212 | 1252 |
| MATH Level 5 | 27.9% | 36.7% |
| Omni-MATH | — | 21% |
| LiveBench Math | 26.5% | — |
Knowledge Llama 3.1-70B leads
Gemma 2 27B: 19.0 (#280), Llama 3.1-70B: 24.2 (#269)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| GPQA Diamond | 36.5% | 44.2% |
| LMArena Expert | 1172 | 1209 |
| MMLU | 75.7% | 80.1% |
| MMLU-Pro | — | 65.3% |
| Confabulations | 27.1% | — |
| GPQA (HELM) | — | 42.6% |
Multilingual Too close to call
Gemma 2 27B: 38.6 (#226), Llama 3.1-70B: 38.8 (#225)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1217 | 1219 |
| LMArena Chinese | 1221 | 1215 |
| LMArena French | 1247 | 1261 |
| LMArena German | 1209 | 1222 |
| LMArena Japanese | 1175 | 1132 |
| LMArena Korean | 1174 | 1140 |
| LMArena Russian | 1234 | 1234 |
| LMArena Spanish | 1228 | 1253 |
Instruction Following Llama 3.1-70B leads
Gemma 2 27B: 60.5 (#249), Llama 3.1-70B: 65.3 (#223)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1231 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 82.1% |
Long Context Too close to call
Gemma 2 27B: 37.3 (#218), Llama 3.1-70B: 37.6 (#214)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1231 | 1241 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Llama 3.1-70B: 35.4 (#267)
| Benchmark | Gemma 2 27B | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1231 | 1261 |
| LMArena Creative Writing | 1241 | 1232 |
| LMArena Multi-Turn | 1224 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 3.1-70B?
Gemma 2 27B and Llama 3.1-70B score almost the same on the Noometry Index (29.4 vs 29.6), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 2 27B or Llama 3.1-70B?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Llama 3.1-70B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-70B does, with 128K tokens against 8K.
How many benchmarks do Gemma 2 27B and Llama 3.1-70B share?
26 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 3.1-70B has 35.