VERIFIEDOct 132026
Is Claude Sonnet 5.5 state of the art?
Yes.SOTA in co-SOTA in Coding and co-SOTA in Coding › Agentic.
As of Oct 13, 2026, Claude Sonnet 5.5 from Anthropic. SOTA in co-SOTA in Coding and co-SOTA in Coding › Agentic. Claude Sonnet 5.5 is tied for SOTA in Coding with Claude Opus 5.5, within the margin of error, since 2026-10-06.
ReasoningNot SOTA · #3#3 · 0dScienceNot SOTA · #3#3 · 0dCodingCo-SOTA#2 · 7dCoding · paretoPareto#2 · 0dCoding › AgenticCo-SOTA#2 · 7dCoding › Agentic · paretoPareto#2 · 0dCoding › Web devNear-SOTA#3 · 0dCoding › Web dev · paretoPareto#3 · 0dLong contextNot SOTA · #10#10 · 0dFactualityNot SOTA · #35#35 · 0d
Why
The ruling, in plain English
Last listed at #3 in Reasoning on 2026-09-28.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| GPQA Diamond claude-sonnet-5-5_max · max | 0.9558080808080808 0.9–1.0 | 2026-09-28 | INDEP. | snap_e03cddec1fbb |
| Terminal-Bench 4.0 Sonnet 5.5 max · max | 61.82 58.9–64.8 | 2026-10-06 | INDEP. | snap_13678220dcf7 |
| LMArena WebDev claude-sonnet-5.5-xhigh · xhigh | 1774.2855361868098 1759.3–1789.2 | 2026-10-08 | INDEP. | snap_d2f3c94c88f6 |
| LMArena Text (style-controlled, longer query) claude-sonnet-5.5-xhigh · xhigh | 1503.308832238542 1489.7–1517.0 | 2026-10-08 | INDEP. | snap_9a4e972507c9 |
| SimpleQA Verified claude-sonnet-5-5_max · max | 0.465 0.4–0.5 | 2026-09-28 | INDEP. | snap_e03cddec1fbb |
Reign history
Where it sits in the succession
Coding
Claude Opus 5.5
Claude Sonnet 5.5
Coding › Agentic
Claude Opus 5.5
Claude Sonnet 5.5
Honest about the gaps
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Reasoning | Not SOTA · #3 | Last listed at #3 in Reasoning on 2026-09-28. |
| Science | Not SOTA · #3 | Last listed at #3 in Science on 2026-09-28. That board does not award a crown. |
| Coding › Web dev | Near-SOTA | Close in Coding › Web dev: rank #3, 25.0 percentile points behind the leader. |
| Long context | Not SOTA · #10 | Ranked #10 in Long context. |
| Factuality | Not SOTA · #35 | Last listed at #35 in Factuality on 2026-09-28. |