VERIFIEDOct 132026
Is Gemini 2.0 Flash Thinking Exp 01.21 state of the art?
No.Best recorded rank is #35 in Reasoning.
As of Oct 13, 2026, Gemini 2.0 Flash Thinking Exp 01.21 from Google DeepMind. Best recorded rank is #35 in Reasoning. Last listed at #35 in Reasoning on 2025-01-21.
Why
The ruling, in plain English
Last listed at #35 in Reasoning on 2025-01-21.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Humanity's Last Exam gemini-2.0-flash-thinking-exp-01-21 | 0.06559999999999999 0.0–0.1 | 2025-01-21 | INDEP. | snap_e03cddec1fbb |
| GPQA Diamond gemini-2.0-flash-thinking-exp-01-21 | 0.5707070707070707 0.5–0.6 | 2025-01-21 | 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 |
|---|---|---|
| Reasoning | Not SOTA · #35 | Last listed at #35 in Reasoning on 2025-01-21. |
| Math | Not SOTA · #35 | Ranked #35 in Math. |
| Science | Not SOTA · #136 | Last listed at #136 in Science on 2025-01-21. That board does not award a crown. |