Meta AI·released 2023-07-181 source
Llama 2-34B benchmark scores: 8 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 8 benchmarks·best result 84.6 on TriviaQA (unverified)·0 of 8 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| TriviaQA | 84.6accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| PIQA | 63.8accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| Winogrande | 53.4accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| MMLU | 50.13accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| OpenBookQA | 44.27accuracy (%) | unverified· optimizedT1 | 2023-07-18Llama 2: Open Foundation and Fine-Tuned Chat Models |
| GSM8K | 42.2accuracy (%) | self-reported· optimizedT1 | 2023-07-18Nemotron-4 15B Technical Report |
| ARC AI2 | 39.33accuracy (%) | unverified· optimizedT1 | 2023-07-18The Falcon Series of Open Language Models |
| BBH | 25.47accuracy (%) | self-reported· optimizedT1 | 2023-07-18Nemotron-4 15B Technical Report |
Claims drawn from cited facts, not live model generation.
This model was developed by Meta AI and released in 2023. With 34 billion parameters, it sits at the large end of the scale, offering substantial headroom for complex tasks but requiring greater compute and memory than more compact models.
3 cited facts
This model is assessed across 8 tracked benchmarks, and of those it holds no current top score. Because these scores are self-reported and have not been independently confirmed, the record should be read as vendor claims rather than verified results.
3 cited facts
With an average SOTA gap of 35.17 points, this model trails the leader by a wide margin — well behind the front of the pack. It holds the top score on 0 benchmarks, so it has no category leadership yet.
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 2-34B is an AI model developed by Meta AI, released 2023-07-18. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Llama 2-34B has recorded scores on 8 benchmarks, each shown with its evidence status.
Llama 2-34B has recorded scores on 8 benchmarks — PIQA, OpenBookQA, Winogrande, TriviaQA, MMLU, ARC AI2, and 2 more. The full table above shows each score with its evidence status.
0 of 8 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Llama 2-34B has 8 tracked claims: 2 self-reported, 6 unverified.