VERIFIEDOct 132026
Is GPT-5.4 Mini state of the art?
No.Best recorded rank is #5 in General LLM.
As of Oct 13, 2026, GPT-5.4 Mini from OpenAI. Best recorded rank is #5 in General LLM. Last listed at #5 in General LLM on 2026-03-18.
Why
The ruling, in plain English
Last listed at #5 in General LLM on 2026-03-18.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) gpt-5.4-mini-high · high | 1471.7515054165244 1451.7–1491.8 | 2026-03-18 | INDEP. | snap_9a4e972507c9 |
| LMArena Text (style-controlled, hard prompts) gpt-5.4-mini-high · high | 1497.5340111531889 1470.5–1524.6 | 2026-03-18 | INDEP. | snap_9a4e972507c9 |
| GPQA Diamond gpt-5.4-mini-2026-03-17_xhigh · xhigh | 0.8686868686868687 0.8–0.9 | 2026-03-17 | INDEP. | snap_e03cddec1fbb |
| LMArena Vision (style-controlled) gpt-5.4-mini-high · high | 1248.2826629006336 1236.5–1260.1 | 2026-04-14 | INDEP. | snap_ae2e1c2545e6 |
| SimpleQA Verified gpt-5.4-mini-2026-03-17_high · high | 0.294 0.3–0.3 | 2026-03-17 | INDEP. | snap_e03cddec1fbb |
| ARC-AGI gpt-5.4-mini-2026-03-17_xhigh · xhigh | 0.6367 | 2026-03-17 | 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 |
|---|---|---|
| General LLM | Not SOTA · #5 | Last listed at #5 in General LLM on 2026-03-18. |
| Reasoning | Not SOTA · #6 | Last listed at #6 in Reasoning on 2026-03-18. |
| Science | Not SOTA · #62 | Last listed at #62 in Science on 2026-03-17. That board does not award a crown. |
| Vision | Not SOTA · #7 | Last listed at #7 in Vision on 2026-04-14. |
| Factuality | Not SOTA · #63 | Last listed at #63 in Factuality on 2026-03-17. |
| Abstraction (ARC) | Not SOTA · #47 | Last listed at #47 in Abstraction (ARC) on 2026-03-17. That board does not award a crown. |