Model comparison
Gemma 2 27B vs Llama 3-8B
Gemma 2 27B is the stronger model overall, scoring 29.4 to 25.5 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MetaSummary
- They share 25 benchmarks with published results for both. Gemma 2 27B scores higher in 8 categories and Llama 3-8B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 2 27B leads 19.0 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 6.1% for Llama 3-8B.
Side by side
| Gemma 2 27B | Llama 3-8B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.4 | 25.5 |
| Released | 2024-06-24 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 34 |
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 3-8B: 31.0 (#289)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 31.9% |
| LMArena Coding | 1211 | 1152 |
| BigCodeBench Complete | 52.5% | 36.9% |
| LiveBench Coding | 36% | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Too close to call
Gemma 2 27B: 15.3 (#315), Llama 3-8B: 14.3 (#326)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1133 |
| DTBench | 48% | 43.9% |
| Epoch Capabilities Index | 122.08 | 116.45 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| LiveBench | 38.2% | — |
| WinoGrande | — | 75.7% |
Math Gemma 2 27B leads
Gemma 2 27B: 10.7 (#311), Llama 3-8B: 8.8 (#323)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 1.9% |
| LMArena Math | 1212 | 1151 |
| MATH Level 5 | 27.9% | 6.1% |
| LiveBench Math | 26.5% | — |
Knowledge Gemma 2 27B leads
Gemma 2 27B: 19.0 (#280), Llama 3-8B: 7.8 (#308)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 36.5% | 26.1% |
| LMArena Expert | 1172 | 1113 |
| MMLU | 75.7% | 68.8% |
| Confabulations | 27.1% | — |
| ARC (AI2) Challenge | — | 82.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Gemma 2 27B leads
Gemma 2 27B: 38.6 (#226), Llama 3-8B: 30.8 (#261)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1217 | 1098 |
| LMArena Chinese | 1221 | 1076 |
| LMArena French | 1247 | 1159 |
| LMArena German | 1209 | 1104 |
| LMArena Japanese | 1175 | 967 |
| LMArena Korean | 1174 | 1004 |
| LMArena Russian | 1234 | 1109 |
| LMArena Spanish | 1228 | 1173 |
Instruction Following Gemma 2 27B leads
Gemma 2 27B: 60.5 (#249), Llama 3-8B: 58.4 (#260)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1127 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), Llama 3-8B: 34.2 (#251)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1231 | 1128 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Llama 3-8B: 37.5 (#256)
| Benchmark | Gemma 2 27B | Llama 3-8B |
|---|---|---|
| LMArena Text | 1231 | 1166 |
| LMArena Creative Writing | 1241 | 1150 |
| LMArena Multi-Turn | 1224 | 1152 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 3-8B?
Gemma 2 27B is the stronger model overall, scoring 29.4 to 25.5 on the Noometry Index.
Is Gemma 2 27B or Llama 3-8B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 31.0 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Llama 3-8B share?
25 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 3-8B has 34.