Model comparison
Gemma 3 27B vs Llama 3.1-405B
Gemma 3 27B and Llama 3.1-405B score almost the same on the Noometry Index (30.8 vs 30.7), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
Google
MetaSummary
- They share 25 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and Llama 3.1-405B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 38.9.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 49.8% for Llama 3.1-405B.
Side by side
| Gemma 3 27B | Llama 3.1-405B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 30.7 |
| Released | 2025-03-11 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Gemma 3 27B: 22.5 (#334), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1322 | 1291 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| WeirdML | — | 21.4% |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Gemma 3 27B leads
Gemma 3 27B: 25.1 (#110), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Too close to call
Gemma 3 27B: 16.7 (#301), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 45% |
| LMArena Hard Prompts | 1340 | 1269 |
| DTBench | 52.5% | 61.4% |
| Epoch Capabilities Index | 130.04 | 128.75 |
| SimpleBench | — | 23% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 50% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Gemma 3 27B leads
Gemma 3 27B: 25.9 (#265), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 9.7% |
| LMArena Math | 1312 | 1281 |
| MATH Level 5 | 74% | 49.8% |
| Omni-MATH | — | 24.9% |
| LiveBench Math | 55.4% | — |
Knowledge Llama 3.1-405B leads
Gemma 3 27B: 25.5 (#261), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 47.7% | 50.9% |
| Confabulations | 40.3% | 17.6% |
| LMArena Expert | 1304 | 1243 |
| MMLU-Pro | — | 72.3% |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Llama 3.1-405B: —
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1334 | 1248 |
| LMArena Chinese | 1346 | 1242 |
| LMArena French | 1368 | 1279 |
| LMArena German | 1362 | 1252 |
| LMArena Japanese | 1287 | 1208 |
| LMArena Korean | 1308 | 1184 |
| LMArena Russian | 1349 | 1265 |
| LMArena Spanish | 1349 | 1260 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1259 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
Gemma 3 27B: 27.6 (#293), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1333 | 1266 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Gemma 3 27B | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1358 | 1284 |
| LMArena Creative Writing | 1346 | 1262 |
| EQ-Bench Creative Writing | 1266 | 870 |
| LMArena Multi-Turn | 1345 | 1297 |
| Short-Story Creative Writing | 79.9% | — |
| WildBench | — | 78.3% |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Llama 3.1-405B?
Gemma 3 27B and Llama 3.1-405B score almost the same on the Noometry Index (30.8 vs 30.7), so choose on price, context window or the category you care about most.
Is Gemma 3 27B or Llama 3.1-405B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Llama 3.1-405B share?
25 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Llama 3.1-405B has 42.