Model comparison
Gemma 2 27B vs Llama 3.2 90B
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.5 on the Noometry Index.
Last verified . 5 shared benchmarks.
Google
MetaSummary
- They share 5 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Llama 3.2 90B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Llama 3.2 90B leads 21.7 to 15.3.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 39.4% for Llama 3.2 90B.
Side by side
| Gemma 2 27B | Llama 3.2 90B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.4 | 27.5 |
| Released | 2024-06-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 2 27B: 34.1 (#246), Llama 3.2 90B: —
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| LMArena Coding | 1211 | — |
| BigCodeBench Complete | 52.5% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning Llama 3.2 90B leads
Gemma 2 27B: 15.3 (#315), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 122.08 | 125.5 |
| EnigmaEval | — | 0.4% |
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1198 | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
Math Too close to call
Gemma 2 27B: 10.7 (#311), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 2.6% |
| MATH Level 5 | 27.9% | 39.4% |
| LiveBench Math | 26.5% | — |
| LMArena Math | 1212 | — |
Knowledge Llama 3.2 90B leads
Gemma 2 27B: 19.0 (#280), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 36.5% | 41% |
| MMLU | 75.7% | 80.3% |
| Confabulations | 27.1% | — |
| LMArena Expert | 1172 | — |
Multimodal Not comparable
Gemma 2 27B: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Gemma 2 27B: 38.6 (#226), Llama 3.2 90B: —
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1217 | — |
| LMArena Chinese | 1221 | — |
| LMArena French | 1247 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1228 | — |
Instruction Following Not comparable
Gemma 2 27B: 60.5 (#249), Llama 3.2 90B: —
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| LiveBench Instruction Following | 58.1% | — |
| LMArena Instruction Following | 1206 | — |
Long Context Not comparable
Gemma 2 27B: 37.3 (#218), Llama 3.2 90B: —
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1231 | — |
Writing & Preference Not comparable
Gemma 2 27B: 44.2 (#225), Llama 3.2 90B: —
| Benchmark | Gemma 2 27B | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1231 | — |
| LMArena Creative Writing | 1241 | — |
| LMArena Multi-Turn | 1224 | — |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 3.2 90B?
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.5 on the Noometry Index.
How many benchmarks do Gemma 2 27B and Llama 3.2 90B share?
5 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 3.2 90B has 9.