Meta AI·released 2023-02-241 source
LLaMA-13B benchmark scores: 11 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 11 benchmarks·best result 77.9 on TriviaQA (unverified)·0 of 11 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| TriviaQA | 77.9accuracy (%) | unverified· optimizedT1 | 2023-02-24Llama 2: Open Foundation and Fine-Tuned Chat Models |
| LAMBADA | 75.2accuracy (%) | self-reported· optimizedT1 | 2023-02-24Qwen Technical Report |
| HellaSwag | 72.27accuracy (%) | unverified· optimizedT1 | 2023-02-24LLaMA: Open and Efficient Foundation Language Models |
| PIQA | 60.2accuracy (%) | self-reported· optimizedT1 | 2023-02-24Qwen Technical Report |
| Winogrande | 46accuracy (%) | unverified· optimizedT1 | 2023-02-24LLaMA: Open and Efficient Foundation Language Models |
| OpenBookQA | 41.87accuracy (%) | unverified· optimizedT1 | 2023-02-24Llama 2: Open Foundation and Fine-Tuned Chat Models |
| ARC AI2 | 36.93accuracy (%) | self-reported· optimizedT1 | 2023-02-24Qwen Technical Report |
| MMLU | 30.27accuracy (%) | unverified· optimizedT1 | 2023-02-24Llama 2: Open Foundation and Fine-Tuned Chat Models |
| ScienceQA | 24.44accuracy (%) | unverified· optimizedT1 | 2023-02-24ScienceQA leaderboard |
| GSM8K | 20.55accuracy (%) | unverified· optimizedT1 | 2023-02-24Stanford HELM |
| BBH | 17.2accuracy (%) | unverified· optimizedT1 | 2023-02-24Baichuan 2: Open Large-scale Language Models |
Claims drawn from cited facts, not live model generation.
This model from Meta AI is a mid-size 13.0 billion parameter system released in 2023, placing it between compact and frontier-scale options in a trade-off between efficiency and lower cost at the smaller end and greater capability headroom and expense at the larger end.
3 cited facts
This model is tracked on 11 benchmarks. It currently holds no top score on any of them. Its results are vendor-reported and have not yet been independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
On average, this model trails the top score on its benchmarks by 39.99 points under the disclosed harness, a wide gap that reads as well behind the leaders. It holds the top score on 0 benchmarks, meaning there is no category leadership to report.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
LLaMA-13B is an AI model developed by Meta AI, released 2023-02-24. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
LLaMA-13B has recorded scores on 11 benchmarks, each shown with its evidence status.
LLaMA-13B has recorded scores on 11 benchmarks — PIQA, OpenBookQA, Winogrande, TriviaQA, MMLU, ScienceQA, and 5 more. The full table above shows each score with its evidence status.
0 of 11 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
LLaMA-13B has 11 tracked claims: 3 self-reported, 8 unverified.