Model comparison
Gemma 2B vs Llama-3.3-70B-Instruct
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 29.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
MetaSummary
- They share 13 benchmarks with published results for both. Gemma 2B scores higher in 3 categories and Llama-3.3-70B-Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.8 to 24.1.
Side by side
| Gemma 2B | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.1 | 30.3 |
| Released | 2024-02-21 | 2024-12-06 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.32 |
| Results tracked | 23 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Gemma 2B: 28.9 (#300), Llama-3.3-70B-Instruct: 30.6 (#284)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Coding | 1010 | 1268 |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Llama-3.3-70B-Instruct: 25.6 (#100)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Gemma 2B leads
Gemma 2B: 17.9 (#275), Llama-3.3-70B-Instruct: 13.7 (#325)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Hard Prompts | 989 | 1257 |
| Epoch Capabilities Index | 93.57 | 127.32 |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| BIG-Bench Hard | 35.2% | — |
| ForecastBench | — | 58.6 |
| HellaSwag | 71.4% | — |
| LiveBench | — | 50.2% |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 2B leads
Gemma 2B: 27.6 (#237), Llama-3.3-70B-Instruct: 14.3 (#292)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Math | 1009 | 1268 |
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Llama-3.3-70B-Instruct: 30.5 (#220)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| MMLU | 42.3% | 86.3% |
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| LMArena Expert | — | 1225 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| TriviaQA | 53.2% | — |
Multilingual Llama-3.3-70B-Instruct leads
Gemma 2B: 23.1 (#289), Llama-3.3-70B-Instruct: 40.1 (#215)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 958 | 1236 |
| LMArena Chinese | 986 | 1217 |
| LMArena Russian | 937 | 1252 |
| LMArena French | — | 1280 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1149 |
| LMArena Korean | — | 1142 |
| LMArena Spanish | — | 1269 |
Instruction Following Llama-3.3-70B-Instruct leads
Gemma 2B: 48.8 (#297), Llama-3.3-70B-Instruct: 71.3 (#152)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 971 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
Long Context Gemma 2B leads
Gemma 2B: 29.9 (#286), Llama-3.3-70B-Instruct: 26.4 (#290)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 981 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Gemma 2B: 24.1 (#303), Llama-3.3-70B-Instruct: 47.8 (#203)
| Benchmark | Gemma 2B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1002 | 1274 |
| LMArena Creative Writing | 986 | 1250 |
| LMArena Multi-Turn | 945 | 1279 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is Gemma 2B better than Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 29.1 on the Noometry Index.
Is Gemma 2B or Llama-3.3-70B-Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 30.6 versus 28.9 in the Noometry coding category.
How many benchmarks do Gemma 2B and Llama-3.3-70B-Instruct share?
13 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama-3.3-70B-Instruct has 43.