Model comparison
Gemini 1.0 Pro vs Llama 2-70B
Gemini 1.0 Pro is the stronger model overall, scoring 27.3 to 24.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
MetaSummary
- They share 22 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 8 categories and Llama 2-70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 1.0 Pro leads 15.6 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 3.3% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Llama 2-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 27.3 | 24.4 |
| Released | 2023-12-13 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.0 Pro: 32.2 (#275), Llama 2-70B: 31.4 (#286)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1108 | 1079 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 17.1 (#296), Llama 2-70B: 14.4 (#325)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1073 |
| DTBench | 45.9% | 41.6% |
| Epoch Capabilities Index | 117.04 | 113.79 |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Gemini 1.0 Pro leads
Gemini 1.0 Pro: 9.3 (#321), Llama 2-70B: 8.1 (#326)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 0% |
| LMArena Math | 1132 | 1091 |
| MATH Level 5 | 11.2% | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Gemini 1.0 Pro leads
Gemini 1.0 Pro: 15.6 (#291), Llama 2-70B: 7.4 (#310)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 34% | 26.3% |
| LMArena Expert | 1059 | 1039 |
| MMLU | 70% | 69.9% |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Gemini 1.0 Pro leads
Gemini 1.0 Pro: 33.4 (#252), Llama 2-70B: 27.7 (#274)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1138 | 1045 |
| LMArena Chinese | 1124 | 995 |
| LMArena French | 1145 | 1090 |
| LMArena German | 1125 | 1041 |
| LMArena Japanese | 1023 | 927 |
| LMArena Russian | 1186 | 1083 |
| LMArena Spanish | 1119 | 1143 |
| LMArena Korean | — | 964 |
Instruction Following Gemini 1.0 Pro leads
Gemini 1.0 Pro: 57.6 (#267), Llama 2-70B: 54.9 (#278)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1071 |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#249), Llama 2-70B: 32.3 (#270)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1132 | 1062 |
Writing & Preference Gemini 1.0 Pro leads
Gemini 1.0 Pro: 36.0 (#264), Llama 2-70B: 32.3 (#279)
| Benchmark | Gemini 1.0 Pro | Llama 2-70B |
|---|---|---|
| LMArena Text | 1149 | 1115 |
| LMArena Creative Writing | 1131 | 1075 |
| LMArena Multi-Turn | 1139 | 1088 |
Frequently asked questions
Is Gemini 1.0 Pro better than Llama 2-70B?
Gemini 1.0 Pro is the stronger model overall, scoring 27.3 to 24.4 on the Noometry Index.
Is Gemini 1.0 Pro or Llama 2-70B better for coding?
They score almost the same on coding (32.2 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Gemini 1.0 Pro and Llama 2-70B share?
22 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Llama 2-70B has 35.