Model comparison
Gemma 1.1 7b IT vs Llama 3-70B
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 28.5 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
MetaSummary
- They share 19 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 3 categories and Llama 3-70B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 1.1 7b IT leads 29.5 to 12.0.
Side by side
| Gemma 1.1 7b IT | Llama 3-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.7 | 28.5 |
| Released | — | 2024-04-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Gemma 1.1 7b IT: 31.0 (#279), Llama 3-70B: 35.3 (#215)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1084 | 1206 |
| HumanEval+ | 35.4% | 72% |
| MBPP+ | 45% | 69% |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
Agentic & Tool Use Not comparable
Gemma 1.1 7b IT: —, Llama 3-70B: 20.9 (#132)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 19.6 (#235), Llama 3-70B: 17.4 (#284)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1195 |
| Kagi LLM Benchmark | — | 35.1% |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 29.5 (#217), Llama 3-70B: 12.0 (#299)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Math | 1107 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 27.8 (#242), Llama 3-70B: 20.8 (#272)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1039 | 1149 |
| GPQA Diamond | — | 40.6% |
| MMLU | — | 79.3% |
Multilingual Llama 3-70B leads
Gemma 1.1 7b IT: 28.3 (#268), Llama 3-70B: 33.8 (#246)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1052 | 1142 |
| LMArena Chinese | 1060 | 1114 |
| LMArena French | 1064 | 1231 |
| LMArena German | 1054 | 1169 |
| LMArena Japanese | 971 | 1017 |
| LMArena Korean | 988 | 1017 |
| LMArena Russian | 1046 | 1159 |
| LMArena Spanish | 1049 | 1241 |
Instruction Following Llama 3-70B leads
Gemma 1.1 7b IT: 54.3 (#278), Llama 3-70B: 62.8 (#233)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1057 | 1194 |
Long Context Llama 3-70B leads
Gemma 1.1 7b IT: 32.0 (#267), Llama 3-70B: 35.6 (#235)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1056 | 1174 |
Writing & Preference Llama 3-70B leads
Gemma 1.1 7b IT: 30.6 (#283), Llama 3-70B: 43.0 (#225)
| Benchmark | Gemma 1.1 7b IT | Llama 3-70B |
|---|---|---|
| LMArena Text | 1094 | 1221 |
| LMArena Creative Writing | 1059 | 1210 |
| LMArena Multi-Turn | 1040 | 1223 |
Frequently asked questions
Is Gemma 1.1 7b IT better than Llama 3-70B?
Gemma 1.1 7b IT is the stronger model overall, scoring 30.7 to 28.5 on the Noometry Index.
Is Gemma 1.1 7b IT or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 31.0 in the Noometry coding category.
How many benchmarks do Gemma 1.1 7b IT and Llama 3-70B share?
19 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Llama 3-70B has 31.