Model comparison
Gemma 2 2b IT vs Llama 3.1-70B
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MetaSummary
- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 4 categories and Llama 3.1-70B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2 2b IT leads 32.6 to 13.5.
Side by side
| Gemma 2 2b IT | Llama 3.1-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.1 | 29.6 |
| Released | — | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 17 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 2b IT leads
Gemma 2 2b IT: 32.3 (#273), Llama 3.1-70B: 30.3 (#296)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1112 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use Not comparable
Gemma 2 2b IT: —, Llama 3.1-70B: 25.1 (#112)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Too close to call
Gemma 2 2b IT: 21.4 (#224), Llama 3.1-70B: 21.6 (#220)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1241 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.92 |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 32.6 (#212), Llama 3.1-70B: 13.5 (#304)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1135 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.9 (#231), Llama 3.1-70B: 24.2 (#269)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Expert | 1096 | 1209 |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multilingual Llama 3.1-70B leads
Gemma 2 2b IT: 32.3 (#257), Llama 3.1-70B: 38.8 (#225)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1121 | 1219 |
| LMArena Chinese | 1132 | 1215 |
| LMArena French | 1157 | 1261 |
| LMArena German | 1114 | 1222 |
| LMArena Japanese | 1083 | 1132 |
| LMArena Korean | 1055 | 1140 |
| LMArena Russian | 1118 | 1234 |
| LMArena Spanish | 1140 | 1253 |
Instruction Following Llama 3.1-70B leads
Gemma 2 2b IT: 57.8 (#263), Llama 3.1-70B: 65.3 (#223)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1231 |
| IFEval | — | 82.1% |
Long Context Llama 3.1-70B leads
Gemma 2 2b IT: 34.3 (#250), Llama 3.1-70B: 37.6 (#214)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1130 | 1241 |
Writing & Preference Gemma 2 2b IT leads
Gemma 2 2b IT: 36.5 (#263), Llama 3.1-70B: 35.4 (#267)
| Benchmark | Gemma 2 2b IT | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1156 | 1261 |
| LMArena Creative Writing | 1147 | 1232 |
| LMArena Multi-Turn | 1118 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is Gemma 2 2b IT better than Llama 3.1-70B?
Gemma 2 2b IT is the stronger model overall, scoring 33.1 to 29.6 on the Noometry Index.
Is Gemma 2 2b IT or Llama 3.1-70B better for coding?
Gemma 2 2b IT scores higher on coding benchmarks: 32.3 versus 30.3 in the Noometry coding category.
How many benchmarks do Gemma 2 2b IT and Llama 3.1-70B share?
17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Llama 3.1-70B has 35.