Model comparison
Gemma 2B vs Llama 3.2 1B
Gemma 2B is the stronger model overall, scoring 29.6 to 20.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
MetaSummary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 4 categories and Llama 3.2 1B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2B leads 30.0 to 10.4.
Side by side
| Gemma 2B | Llama 3.2 1B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.6 | 20.1 |
| Released | 2024-02-21 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 60K |
| Max output | — | 54K |
| Input $ / M tokens | — | $0.027 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 23 | 22 |
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 1B: 21.1 (#338)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1010 | 1070 |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Llama 3.2 1B: 14.6 (#150)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10.8% |
| BALROG | — | 6.6% |
Reasoning Gemma 2B leads
Gemma 2B: 18.8 (#275), Llama 3.2 1B: 16.2 (#308)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1044 |
| Epoch Capabilities Index | 94.2 | 101.99 |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 2B leads
Gemma 2B: 30.0 (#239), Llama 3.2 1B: 10.4 (#313)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Math | 1009 | 1086 |
| OTIS Mock AIME 2024-2025 | — | 0.6% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Llama 3.2 1B: 7.2 (#312)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | — | 23.9% |
| LMArena Expert | — | 1007 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Too close to call
Gemma 2B: 23.0 (#294), Llama 3.2 1B: 23.8 (#292)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 958 | 973 |
| LMArena Chinese | 986 | 959 |
| LMArena Russian | 937 | 941 |
| LMArena German | — | 1014 |
Instruction Following Llama 3.2 1B leads
Gemma 2B: 48.5 (#302), Llama 3.2 1B: 52.4 (#290)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 970 | 1031 |
Long Context Llama 3.2 1B leads
Gemma 2B: 29.9 (#291), Llama 3.2 1B: 31.9 (#274)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 981 | 1050 |
Writing & Preference Gemma 2B leads
Gemma 2B: 24.0 (#308), Llama 3.2 1B: 21.3 (#310)
| Benchmark | Gemma 2B | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1002 | 1055 |
| LMArena Creative Writing | 987 | 1033 |
| LMArena Multi-Turn | 945 | 1030 |
| EQ-Bench Creative Writing | — | 200 |
Frequently asked questions
Is Gemma 2B better than Llama 3.2 1B?
Gemma 2B is the stronger model overall, scoring 29.6 to 20.1 on the Noometry Index.
Is Gemma 2B or Llama 3.2 1B better for coding?
Gemma 2B scores higher on coding benchmarks: 29.4 versus 21.1 in the Noometry coding category.
How many benchmarks do Gemma 2B and Llama 3.2 1B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama 3.2 1B has 22.