Model comparison
Gemma 3 4B vs Llama 13b
Gemma 3 4B is the stronger model overall, scoring 28.1 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
Google
MetaSummary
- They share 9 benchmarks with published results for both. Gemma 3 4B scores higher in 4 categories and Llama 13b in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 4B leads 65.2 to 36.7.
Side by side
| Gemma 3 4B | Llama 13b | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 28.1 | 24.4 |
| Released | 2025-03-12 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), Llama 13b: 21.4 (#337)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Coding | 1230 | 683 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Llama 13b: —
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Too close to call
Gemma 3 4B: 13.2 (#335), Llama 13b: 14.0 (#329)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1253 | 728 |
| Epoch Capabilities Index | 116.02 | 100.58 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Llama 13b leads
Gemma 3 4B: 16.8 (#292), Llama 13b: 26.7 (#256)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Math | 1239 | 838 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Llama 13b: —
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Gemma 3 4B: —, Llama 13b: —
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.5 (#194), Llama 13b: 16.6 (#297)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Non-English | 1273 | 819 |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.2 (#225), Llama 13b: 36.7 (#305)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1239 | 781 |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Llama 13b: —
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.0 (#239), Llama 13b: 13.8 (#312)
| Benchmark | Gemma 3 4B | Llama 13b |
|---|---|---|
| LMArena Text | 1291 | 834 |
| LMArena Creative Writing | 1271 | 794 |
| LMArena Multi-Turn | 1255 | 753 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Llama 13b?
Gemma 3 4B is the stronger model overall, scoring 28.1 to 24.4 on the Noometry Index.
Is Gemma 3 4B or Llama 13b better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 21.4 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Llama 13b share?
9 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Llama 13b has 21.