VERIFIEDOct 132026
Is Step 3.5 Flash state of the art?
No.Best current rank is #99 in Factuality.
As of Oct 13, 2026, Step 3.5 Flash from stepfun. Best current rank is #99 in Factuality. Ranked #99 in Factuality.
Why
The ruling, in plain English
Ranked #122 in General LLM.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) step-3.5-flash | 1393.1980204294073 1389.6–1396.8 | 2026-10-08 | INDEP. | snap_51142aff7bb5 |
| LMArena Text (style-controlled, hard prompts) step-3.5-flash | 1412.5505370771946 1408.2–1416.9 | 2026-10-08 | INDEP. | snap_51142aff7bb5 |
| LMArena Text (style-controlled, math) step-3.5-flash | 1407.5267860471 1397.3–1417.7 | 2026-10-08 | INDEP. | snap_51142aff7bb5 |
| LMArena Text (style-controlled, coding) step-3.5-flash | 1449.4918137630827 1443.8–1455.2 | 2026-10-08 | INDEP. | snap_51142aff7bb5 |
| LMArena Text (style-controlled, longer query) step-3.5-flash | 1403.2433925858581 1398.1–1408.4 | 2026-10-08 | INDEP. | snap_51142aff7bb5 |
| LMArena Text factuality step-3.5-flash | 1416.5467220816995 1413.5–1419.6 | 2026-10-08 | INDEP. | snap_ee60de771ba0 |
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 | #122 in this category | Ranked #122 in General LLM. |
| Reasoning | #124 in this category | Ranked #124 in Reasoning. |
| Math | #102 in this category | Ranked #102 in Math. |
| Coding | #110 in this category | Ranked #110 in Coding. |
| Long context | #117 in this category | Ranked #117 in Long context. |
| Factuality | #99 in this category | Ranked #99 in Factuality. |