Meta AI·released 2023-07-13✓ 2 sources
Llama 2-7B benchmark scores: 12 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 12 benchmarks·best result 73.7 on TriviaQA (unverified)·0 of 12 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| TriviaQA | 73.7accuracy (%) | unverified· optimizedT1 | 2023-07-18Gemma: Open Models Based on Gemini Research and Technology |
| LAMBADA | 73.3accuracy (%) | self-reported· optimizedT1 | 2023-07-18Qwen Technical Report |
| HellaSwag | 69.6accuracy (%) | unverified· optimizedT1 | 2023-07-18Gemma: Open Models Based on Gemini Research and Technology |
| PIQA | 57.6accuracy (%) | unverified· optimizedT1 | 2023-07-18Gemma: Open Models Based on Gemini Research and Technology |
| OpenBookQA | 44.8accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| Winogrande | 38.4accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| ARC AI2 | 27.87accuracy (%) | unverified· optimizedT1 | 2023-07-18The Falcon Series of Open Language Models |
| MMLU | 27.73accuracy (%) | unverified· optimizedT1 | 2023-07-18Stanford CRFM Leaderboard |
| ScienceQA | 24.11accuracy (%) | unverified· optimizedT1 | 2023-07-18ScienceQA leaderboard |
| BBH | 18.88accuracy (%) | unverified· optimizedT1 | 2023-07-18Gemma: Open Models Based on Gemini Research and Technology |
| GSM8K | 16.7accuracy (%) | unverified· optimizedT1 | 2023-07-18Gemma: Open Models Based on Gemini Research and Technology |
| Chess Puzzles | 0accuracy (%) | unverifiedT2 | 2023-07-18 |
Claims drawn from cited facts, not live model generation.
Developed by Meta AI, this model is a compact 6.74-billion-parameter system released in 2023. That compact scale favors efficiency and lower cost, trading away the greater headroom and higher expense of larger models.
4 cited facts
This model is scored on 12 tracked benchmarks, though it holds no current top score on any of them. Its results are self-reported: the numbers are vendor-claimed and have not been independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
On average, it trails the best score by 45.23 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 yet.
2 cited facts
2 facts cross-checked across data sources: 1 corroborated, 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, huggingface_models
Llama 2-7B is an AI model developed by Meta AI, released 2023-07-13. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Llama 2-7B has recorded scores on 12 benchmarks, each shown with its evidence status.
Llama 2-7B has recorded scores on 12 benchmarks — PIQA, OpenBookQA, Winogrande, TriviaQA, MMLU, ScienceQA, and 6 more. The full table above shows each score with its evidence status.
0 of 12 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Llama 2-7B has 12 tracked claims: 1 self-reported, 11 unverified.