VERIFIEDOct 142026
Is Llama 3.1 405B Instruct state of the art?
It used to be.Was SOTA in General LLM.
As of Oct 14, 2026, Llama 3.1 405B Instruct from Meta. Was SOTA in General LLM. Last listed at #3 in General LLM on 2024-09-04.
Why
The ruling, in plain English
Last listed at #3 in General LLM on 2024-09-04.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) llama-3.1-405b-instruct | 1250.0423051745597 1246.3–1254.2 | 2024-09-04 | INDEP. | snap_368d64825bf4 |
| LMArena Text (style-controlled, hard prompts) llama-3.1-405b-instruct | 1248.7813676450337 1242.5–1256.7 | 2024-09-04 | INDEP. | snap_368d64825bf4 |
| GPQA Diamond Llama-3.1-405B-Instruct | 0.5091540404040404 0.5–0.6 | 2024-07-23 | INDEP. | snap_fee7890b5dd0 |
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 |
|---|---|---|
| General LLM | #3 in this category | Last listed at #3 in General LLM on 2024-09-04. |
| Reasoning | Not enough data | #3 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond |
| Science | #124 in this category | Last listed at #124 in Science on 2024-07-23. That board does not award a crown. |