VERIFIEDOct 142026
Is Llama 3.1 Tulu 3 70B Dpo state of the art?
No.Best recorded rank is #165 in Reasoning.
As of Oct 14, 2026, Llama 3.1 Tulu 3 70B Dpo from Allen Institute for AI,University of Washington. Best recorded rank is #165 in Reasoning. Last listed at #165 in Reasoning on 2024-11-21.
Why
The ruling, in plain English
Last listed at #165 in Reasoning on 2024-11-21.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| GPQA Diamond Llama-3.1-Tulu-3-70B-DPO | 0.46275252525252525 0.4–0.5 | 2024-11-21 | INDEP. | snap_e03cddec1fbb |
Reign history
Where it sits in the succession
No closed or open crown interval includes this model.
Honest about the gaps
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Reasoning | Not SOTA · #165 | Last listed at #165 in Reasoning on 2024-11-21. |
| Science | Not SOTA · #165 | Last listed at #165 in Science on 2024-11-21. That board does not award a crown. |