Llama-3.1-Tulu-3-70B-DPO Benchmark Results

Llama-3.1-Tulu-3-70B-DPO — benchmark results

Ai2's DPO-stage checkpoint of the fully open Tulu 3 post-training recipe, built on Llama 3.1 70B. Provider: Meta. Released 2024-11-20. Access: Open.

Unified ELO 1561 ± 71, rank #589 of 1776 rated models, from 9 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	82.82	Score	99.2
Open LLM Leaderboard - MuSR	23.4	Score	98.3
Open LLM Leaderboard - GPQA	16.78	Score	94
Open LLM Leaderboard - MATH Level 5	44.94	Score	93.3
Open LLM Leaderboard - BBH	45.05	Score	85.4
Open LLM Leaderboard - MMLU-Pro	40.36	Score	85.3
MATH Level 5	42.66	Accuracy (%)	35.2
HREF	11.91	Average HREF Score (%)	33.3
OTIS Mock AIME 2024-25	4.44	Accuracy (%)	12.8