DeepSeek R1 Distill Llama 70B — Benchmarks

Benchmark scores for DeepSeek R1 Distill Llama 70B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Coding

BenchmarkScoreRank
LiveBench Coding51.6#5 / 13

Math

BenchmarkScoreRank
AIME 2024/202551.4%#7 / 22
MATH Level 589.9%#3 / 23
LiveBench Math58.1#6 / 13

Reasoning

BenchmarkScoreRank
GPQA Diamond55.7%#10 / 28
LiveBench Reasoning67.6#3 / 13

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.