Model comparison
Gemma 3 12B vs Llama 13b
Gemma 3 12B is the stronger model overall, scoring 31.8 to 23.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
Google
MetaSummary
- They share 9 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 12B leads 47.7 to 13.9.
Side by side
| Gemma 3 12B | Llama 13b | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 31.8 | 23.9 |
| Released | 2025-03-12 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Gemma 3 12B: 31.2 (#276), Llama 13b: 20.9 (#332)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Coding | 1281 | 683 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Llama 13b: —
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Gemma 3 12B leads
Gemma 3 12B: 15.2 (#307), Llama 13b: 13.4 (#327)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1309 | 728 |
| Epoch Capabilities Index | 123.49 | 100.09 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Llama 13b leads
Gemma 3 12B: 21.0 (#273), Llama 13b: 24.4 (#259)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Math | 1307 | 838 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Gemma 3 12B: 26.5 (#250), Llama 13b: —
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Gemma 3 12B: —, Llama 13b: —
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Llama 13b: 16.8 (#292)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1318 | 819 |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.8 (#179), Llama 13b: 36.9 (#300)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1299 | 781 |
Long Context Not comparable
Gemma 3 12B: 40.0 (#157), Llama 13b: —
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1317 | — |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Llama 13b: 13.9 (#307)
| Benchmark | Gemma 3 12B | Llama 13b |
|---|---|---|
| LMArena Text | 1334 | 834 |
| LMArena Creative Writing | 1331 | 794 |
| LMArena Multi-Turn | 1334 | 753 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Llama 13b?
Gemma 3 12B is the stronger model overall, scoring 31.8 to 23.9 on the Noometry Index.
Is Gemma 3 12B or Llama 13b better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.2 versus 20.9 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Llama 13b share?
9 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Llama 13b has 21.