HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/perplexity-ai/perplexity-ai/r1-1776-distill-llama-70b

perplexity-ai/r1-1776-distill-llama-70b

family llama · 3 variants · unknown

provider
perplexity-ai
released
—
huggingface
https://huggingface.co/perplexity-ai/r1-1776-distill-llama-70b
best scores
AIME 2024: 70.0MATH-500: 94.5MMLU: 88.52DROP: 84.55GPQA: 65.2

Best scores per benchmark

benchmarkcategorybest score
MATH-500math94.5
MMLUknowledge88.52
DROPreasoning84.55
AIME 2024math70.0
GPQAreasoning65.2

Variants (3)

variantkindquantbitsvRAMdlorgyear
r1-1776-distill-llama-70b-GGUFggufgguf16.02,342unsloth2025
perplexity-ai_r1-1776-distill-llama-70b-GGUFggufgguf1.02,104bartowski2025
r1-1776-distill-llama-70b-GGUFggufgguf3.0844lmstudio-community2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.