Model comparison
Gemini 1.0 Pro vs Llama 2-7B
Llama 2-7B is the stronger model overall, scoring 28.6 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
MetaSummary
- They share 17 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 6 categories and Llama 2-7B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-7B leads 28.2 to 8.7.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Llama 2-7B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 27.1 | 28.6 |
| Released | 2023-12-13 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Gemini 1.0 Pro: 31.6 (#270), Llama 2-7B: 28.7 (#302)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1108 | 1002 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 16.4 (#292), Llama 2-7B: 15.1 (#309)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1009 |
| Epoch Capabilities Index | 116.97 | 98.54 |
| Chess Puzzles | — | 0% |
| DTBench | 45.9% | — |
| BIG-Bench Hard | — | 39.2% |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Llama 2-7B leads
Gemini 1.0 Pro: 8.7 (#315), Llama 2-7B: 28.2 (#231)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Math | 1132 | 1042 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
| GSM8K | — | 16.7% |
Knowledge Llama 2-7B leads
Gemini 1.0 Pro: 15.5 (#286), Llama 2-7B: 27.7 (#243)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1059 | 1036 |
| MMLU | 70% | 45.8% |
| GPQA Diamond | 34% | — |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Gemini 1.0 Pro: —, Llama 2-7B: —
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |
Multilingual Gemini 1.0 Pro leads
Gemini 1.0 Pro: 33.5 (#247), Llama 2-7B: 23.9 (#288)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1138 | 973 |
| LMArena Chinese | 1124 | 973 |
| LMArena French | 1144 | 969 |
| LMArena German | 1125 | 978 |
| LMArena Russian | 1186 | 995 |
| LMArena Spanish | 1118 | 1007 |
| LMArena Japanese | 1023 | — |
Instruction Following Gemini 1.0 Pro leads
Gemini 1.0 Pro: 57.9 (#262), Llama 2-7B: 51.0 (#293)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1006 |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#244), Llama 2-7B: 30.4 (#282)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1132 | 999 |
Writing & Preference Gemini 1.0 Pro leads
Gemini 1.0 Pro: 36.2 (#259), Llama 2-7B: 28.1 (#293)
| Benchmark | Gemini 1.0 Pro | Llama 2-7B |
|---|---|---|
| LMArena Text | 1149 | 1053 |
| LMArena Creative Writing | 1130 | 1033 |
| LMArena Multi-Turn | 1139 | 1029 |
Frequently asked questions
Is Gemini 1.0 Pro better than Llama 2-7B?
Llama 2-7B is the stronger model overall, scoring 28.6 to 27.1 on the Noometry Index.
Is Gemini 1.0 Pro or Llama 2-7B better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 31.6 versus 28.7 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Llama 2-7B share?
17 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Llama 2-7B has 29.