Model comparison
GPT-4V vs Llama 2-7B
Llama 2-7B has enough public results to be ranked (#315); GPT-4V does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MetaSummary
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| GPT-4V | Llama 2-7B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 35.8 | 28.6 |
| Released | 2023-11-06 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 1 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4V: —, Llama 2-7B: 28.7 (#302)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Coding | — | 1002 |
Reasoning Not comparable
GPT-4V: —, Llama 2-7B: 15.1 (#309)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1009 |
| BIG-Bench Hard | — | 39.2% |
| Epoch Capabilities Index | — | 98.54 |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Not comparable
GPT-4V: —, Llama 2-7B: 28.2 (#231)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Math | — | 1042 |
| GSM8K | — | 16.7% |
Knowledge Not comparable
GPT-4V: —, Llama 2-7B: 27.7 (#243)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Expert | — | 1036 |
| ARC (AI2) Challenge | — | 45.9% |
| BoolQ | — | 77.9% |
| MMLU | — | 45.8% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
GPT-4V: 32.5, Llama 2-7B: —
Multilingual Not comparable
GPT-4V: —, Llama 2-7B: 23.9 (#288)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Non-English | — | 973 |
| LMArena Chinese | — | 973 |
| LMArena French | — | 969 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |
Instruction Following Not comparable
GPT-4V: —, Llama 2-7B: 51.0 (#293)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | — | 1006 |
Long Context Not comparable
GPT-4V: —, Llama 2-7B: 30.4 (#282)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | — | 999 |
Writing & Preference Not comparable
GPT-4V: —, Llama 2-7B: 28.1 (#293)
| Benchmark | GPT-4V | Llama 2-7B |
|---|---|---|
| LMArena Text | — | 1053 |
| LMArena Creative Writing | — | 1033 |
| LMArena Multi-Turn | — | 1029 |
Frequently asked questions
Is GPT-4V better than Llama 2-7B?
Llama 2-7B has enough public results to be ranked (#315); GPT-4V does not yet, so treat this comparison as directional.
How many benchmarks do GPT-4V and Llama 2-7B share?
0 benchmarks have published results for both models. GPT-4V has 1 scored results on Noometry and Llama 2-7B has 29.