Ai2
Tulu 3 (Tülu 3) 70B benchmark results
4 results on 4 benchmarks from 2 sources.
Open weights Released: Nov 21, 2024 Updated Oct 22, 2026
Also listed as: Llama-3.1-Tulu-3-70B-DPO · allenai/Llama-3.1-Tulu-3-70B-DPO
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 42.2% | 107 | Average of 6 normalised benchmarks; bfloat16; 70B params“allenai/Llama-3.1-Tulu-3-70B-DPO” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 46.3% | 222 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 4.4% | 236 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Mar 7, 2025 |
| MATH Level 5 | 42.7% | 68 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these Tulu 3 (Tülu 3) 70B scores come from?
From Epoch AI Benchmarking Hub and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.