Model comparison
Gemma 3 4B vs Llama 2-34B
Gemma 3 4B has enough public results to be ranked (#326); Llama 2-34B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Google
MetaSummary
- They share 1 benchmark with published results for both.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Llama 2-34B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 28.1 | — |
| Released | 2025-03-12 | 2023-07-18 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemma 3 4B: 35.9 (#215), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Not comparable
Gemma 3 4B: 13.2 (#335), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| Epoch Capabilities Index | 116.02 | 105.2 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| BIG-Bench Hard | — | 44.1% |
| PIQA | — | 81.9% |
| WinoGrande | — | 76.7% |
Math Not comparable
Gemma 3 4B: 16.8 (#292), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |
| GSM8K | — | 42.2% |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
| ARC (AI2) Challenge | — | 54.5% |
| BoolQ | — | 83.7% |
| MMLU | — | 62.6% |
| OpenBookQA | — | 58.2% |
| TriviaQA | — | 84.6% |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), Llama 2-34B: —
| Benchmark | Gemma 3 4B | Llama 2-34B |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1271 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |
Frequently asked questions
Is Gemma 3 4B better than Llama 2-34B?
Gemma 3 4B has enough public results to be ranked (#326); Llama 2-34B does not yet, so treat this comparison as directional.
How many benchmarks do Gemma 3 4B and Llama 2-34B share?
1 benchmark has published results for both models. Gemma 3 4B has 22 scored results on Noometry and Llama 2-34B has 10.