Model comparison
Gemma 2B vs Llama 3.2 3B
Gemma 2B and Llama 3.2 3B score almost the same on the Noometry Index (29.6 vs 28.9), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Google
MetaSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Llama 3.2 3B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.2 3B leads 56.0 to 48.5.
Side by side
| Gemma 2B | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.6 | 28.9 |
| Released | 2024-02-21 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2B leads
Gemma 2B: 29.4 (#305), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1010 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Llama 3.2 3B leads
Gemma 2B: 18.8 (#275), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1095 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Llama 3.2 3B leads
Gemma 2B: 30.0 (#239), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1009 | 1126 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Llama 3.2 3B: 29.7 (#235)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | — | 1090 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Llama 3.2 3B leads
Gemma 2B: 23.0 (#294), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 958 | 1019 |
| LMArena Chinese | 986 | 1017 |
| LMArena Russian | 937 | 949 |
| LMArena German | — | 1056 |
Instruction Following Llama 3.2 3B leads
Gemma 2B: 48.5 (#302), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 970 | 1089 |
Long Context Llama 3.2 3B leads
Gemma 2B: 29.9 (#291), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 981 | 1100 |
Writing & Preference Too close to call
Gemma 2B: 24.0 (#308), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Gemma 2B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1002 | 1110 |
| LMArena Creative Writing | 987 | 1094 |
| LMArena Multi-Turn | 945 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
Frequently asked questions
Is Gemma 2B better than Llama 3.2 3B?
Gemma 2B and Llama 3.2 3B score almost the same on the Noometry Index (29.6 vs 28.9), so choose on price, context window or the category you care about most.
Is Gemma 2B or Llama 3.2 3B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 27.6 in the Noometry coding category.
How many benchmarks do Gemma 2B and Llama 3.2 3B share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama 3.2 3B has 18.