whatmodel.sh / LLaMA 7B
LLaMA 7B
↗ share
+ contribute
LLaMA 7B is an open-weights language model from Meta, released February 2023. Its published size is 6.7B parameters. Licence: llama-1-noncommercial-research.
Catalogue identity notes
Original LLaMA (v1) base model (Touvron et al. 2023), released by Meta to approved researchers under a non-commercial licence; no official public download exists, so no run command is listed (community re-uploads such as huggyllama/* are unofficial).
$ how it compares
The LLMs ranked either side of LLaMA 7B, out of 828 with a score, then more from Meta.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 741 | Llama 2 7B Chat | 30±1 | local | ||
| 742 |  Baichuan2-7B-Base | 30±1 | local | ||
| 743 | LLaMA 7B | 30±1 | comparison only | ||
| 744 |  MPT-7B (base) | 30±1 | comparison only | ||
| 745 |  OLMo 7B Instruct | 29±2 | local | ||
| more from Meta | |||||
| 24 | Muse Spark 1.3 | 77±1 | api $2.00/M | ||
| 40 | Muse Spark 1.2 | 75±1 | api $2.00/M | ||
| 43 | Muse Spark 1.1 | 75±1 | api $2.00/M | ||
$ what it's good at
coding▁▁▃▃▅▇█▇▅▄▃▁ #511 of 524 · 7.0% of its score · 2 tests
Beats Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B, Qwen3 0.6B here, though they rank higher overall. Trails Falcon3 1B Instruct, Gemma 2B IT, Granite 3.0 1B-A400M Instruct here, though they rank lower overall.
math▃▂▃▅▇▅▅█▄▁▁▁ #459 of 462 * · 3.3% of its score · 2 tests
Beats DeepSeek-Coder 1.3B Base, StarCoderBase 7B here, though they rank higher overall. Trails Qwen2 0.5B Instruct, Granite 4.0 350M, Granite 4.0 H 350M here, though they rank lower overall.
other tests14 not in a task · 90% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ARC Challenge +3 | 44.6% ✎ | ▁·▁··▁▁▇▂█▆▃ beats 20/26 | 28% |
| WinoGrande +3 | 69.9% ✎ | ▁····▁··▁▂█▄ beats 23/26 | 12% |
| BoolQ +3 | 75.0% ✎ | ▂▃▂▅▆▂▅▆█▂▂▂ beats 22/26 | 9.4% |
| HellaSwag +3 | 76.2% ✎ | ▃···▁▇▅█▇▃▁▁ beats 21/26 | 7.1% |
| ARC Easy +3 | 72.9% ✎ | ▁▁·▁▁▄▅▄█▅▁▃ beats 22/26 | 6.6% |
| OpenBookQA +3 | 34.4% ✎ | █·▁▁▃·▁▃▅▇▃▄ beats 23/26 | 6.4% |
| PIQA +3 | 78.7% ✎ | ▁·▁··▁▁▃█▅█▂ beats 19/26 | 3.9% |
| SciQ +1 | 94.6% ✎ | ▁·▁·▁·▃▅▃█▄▁ beats 23/26 | 3.4% |
6 more tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BIG-Bench Hard | 30.9% ✎ | ███··█·█·█·█ beats 1/6 | 3.3% |
| Social IQA +2 | 44.8% ✎ | ▁···▁▃█▁▃▁·▁ beats 22/26 | 2.6% |
| MMLU +1 | 35.2% ✎ | ▄▄·▄···▄▄·██ beats 3/8 | 2.6% |
| Factual knowledge recall, Premium2k exact match (zero-shot) | 14.6% ✎ | ▅····▃▅·██·█ beats 3/13 | 1.7% |
| Factual knowledge recall, Premium2k exact match (10-shot) | 35.0% ✎ | ▃▅▃··▅▃·█▃▃▅ beats 6/13 | 1.4% |
| LAMBADA (OpenAI version), last-word accuracy | 73.5% ✎ | ▁··▂▁▁▁▂▆█▅▃ beats 22/26 | 1.0% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Stability AI — original Stabl… 38%, OLMo: Accelerating the Scienc… 18%, LLaMA: Open and Efficient Fou… 18% and 3 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Stability AI — original StableLM zero-shot evaluation outputs | 10 | 38% |
 OLMo: Accelerating the Science of Language Models — authors' own runs | 8 | 18% |
| LLaMA: Open and Efficient Foundation Language Models — authors' own runs · lab-reported | 13 | 18% |
| Textbooks Are All You Need II: phi-1.5 technical report — authors' own runs | 8 | 15% |
| InstructEval (DeCLaRe Lab) README results table | 3 | 8% |
| Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1) | 2 | 3% |
| prior · pull toward the middle | 0% | |
| weighted average | = 29.5 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json