Model comparison
Gemma 3 27B vs Llama 2-13B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
MetaSummary
- They share 20 benchmarks with published results for both. Gemma 3 27B scores higher in 4 categories and Llama 2-13B 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 29.8.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemma 3 27B and 42.2% for Llama 2-13B.
Side by side
| Gemma 3 27B | Llama 2-13B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 29.6 |
| Released | 2025-03-11 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.16 | — |
| Results tracked | 43 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Gemma 3 27B: 22.5 (#334), Llama 2-13B: 30.9 (#291)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1322 | 1062 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Llama 2-13B: —
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Gemma 3 27B leads
Gemma 3 27B: 16.7 (#301), Llama 2-13B: 12.8 (#337)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1340 | 1051 |
| DTBench | 52.5% | 42.2% |
| Epoch Capabilities Index | 130.04 | 106.17 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| LiveBench | 50% | — |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
Gemma 3 27B: 25.9 (#265), Llama 2-13B: 31.1 (#229)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Math | 1312 | 1065 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
| GSM8K | — | 36.9% |
Knowledge Llama 2-13B leads
Gemma 3 27B: 25.5 (#261), Llama 2-13B: 28.1 (#249)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1304 | 1030 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Llama 2-13B: —
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
| ScienceQA | — | 55.8% |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Llama 2-13B: 26.5 (#279)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1334 | 1024 |
| LMArena Chinese | 1346 | 1001 |
| LMArena French | 1368 | 1044 |
| LMArena German | 1362 | 1009 |
| LMArena Japanese | 1287 | 894 |
| LMArena Korean | 1308 | 953 |
| LMArena Russian | 1349 | 1055 |
| LMArena Spanish | 1349 | 1087 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Llama 2-13B: 53.3 (#287)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1045 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Llama 2-13B leads
Gemma 3 27B: 27.6 (#293), Llama 2-13B: 32.3 (#269)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1333 | 1064 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Llama 2-13B: 29.8 (#289)
| Benchmark | Gemma 3 27B | Llama 2-13B |
|---|---|---|
| LMArena Text | 1358 | 1084 |
| LMArena Creative Writing | 1346 | 1047 |
| LMArena Multi-Turn | 1345 | 1050 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Llama 2-13B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Is Gemma 3 27B or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 3 27B and Llama 2-13B share?
20 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Llama 2-13B has 32.