family llama · 1 variants · unknown
| benchmark | category | best score |
|---|---|---|
| BBH | reasoning | 88.0 |
| HumanEval | coding | 86.2 |
| MMLU | knowledge | 84.4 |
| GSM8K | math | 76.2 |
| IFEval | instruction-following | 72.8 |
| MATH | math | 63.4 |
| DROP | reasoning | 61.3 |
| PopQA | knowledge | 55.7 |
| TruthfulQA | safety | 46.8 |
| AlpacaEval | chat | 12.4 |
| variant | kind | quant | bits | vRAM | dl | org | year |
|---|---|---|---|---|---|---|---|
| Llama-3.1-Tulu-3-405B-DPO | original | bf16 | 16.0 | 56 | allenai | 2025 |