VERIFIEDOct 142026
Is Claude 3 Sonnet state of the art?
No.Best recorded rank is #154 in Science.
As of Oct 14, 2026, Claude 3 Sonnet from Anthropic. Best recorded rank is #154 in Science. Last listed at #154 in Science on 2024-02-29. That board does not award a crown.
Why
The ruling, in plain English
#154 on GPQA Diamond; missing Humanity's Last Exam and LMArena Text (style-controlled, hard prompts)
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| GPQA Diamond claude-3-sonnet-20240229 | 0.4059343434343434 0.4–0.5 | 2024-02-29 | INDEP. | snap_fee7890b5dd0 |
| LMArena Vision (style-controlled) claude-3-sonnet-20240229 | 1016.1085185238421 1004.7–1027.5 | 2026-10-09 | INDEP. | snap_44d0155ee751 |
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 enough data | #154 on GPQA Diamond; missing Humanity's Last Exam and LMArena Text (style-controlled, hard prompts) |
| Science | #154 in this category | Last listed at #154 in Science on 2024-02-29. That board does not award a crown. |
| Vision | Not enough data | #109 on LMArena Vision (style-controlled); missing GDP.pdf |