Meta AI·released 2024-04-181 source
Llama 3-70B benchmark scores: 7 benchmarks tracked. 43% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 72.4 on MMLU (unverified)·3 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 72.4accuracy (%) | unverified· optimizedT1 | 2024-04-18Stanford CRFM Leaderboard |
| Winogrande | 67accuracy (%) | unverified· optimizedT1 | 2024-04-18The Llama 3 Herd of Models |
| DTBench | 23.6accuracy (%) | unverifiedT1 | 2024-04-18https://conceptualreasoning.ai/dtbench |
| MATH level 5 | 22.55accuracy (%) | reproduced· optimizedT1 | 2024-04-18Epoch AI |
| GPQA diamond | 20.75accuracy (%) | reproduced· optimizedT1 | 2024-04-18Epoch AI |
| Cybench | 5accuracy (%) | unverified· optimizedT1 | 2024-04-18Cybench leaderboard |
| OTIS Mock AIME 2024-2025 | 4.21accuracy (%) | reproduced· optimizedT1 | 2024-04-18Epoch AI |
Claims drawn from cited facts, not live model generation.
Developed by Meta AI and released in 2024, this model is a large-scale model with 70 billion parameters, which implies more capability headroom but also higher training and inference costs than smaller alternatives.
3 cited facts
This model is scored on 7 tracked benchmarks. It holds no current top score on any of them. The record is independently reproduced, meaning outside evaluation backs the scores up.
3 cited facts
On average this model trails the leading score by 61.41 points, and a gap that wide reads as well behind the leaders — a difference in benchmark score under a disclosed harness, not a statement about capability. It also holds the top score on none of its benchmarks, so there is no category leadership to point to 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 3-70B is an AI model developed by Meta AI, released 2024-04-18. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Llama 3-70B has recorded scores on 7 benchmarks, each shown with its evidence status.
Llama 3-70B has recorded scores on 7 benchmarks — Winogrande, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, MMLU, and 1 more. The full table above shows each score with its evidence status.
3 of 7 recorded scores (43%) are independently reproduced rather than self-reported by the lab.
Llama 3-70B has 7 tracked claims: 3 independently reproduced, 4 unverified.