Is Gemini 2.5 Flash Preview state of the art?#114Best current rank: #114 in Factuality, as of Nov 22, 2026.
As of Nov 22, 2026, Gemini 2.5 Flash Preview is ranked #114 in Factuality (since Nov 22, 2026; sources LMArena Text factuality; methodology v1.0). Ranked #114 in Factuality.
Facts and scores
Gemini 2.5 Flash Preview is a closed-weights text model from Google DeepMind, listed on LMArena since Oct 19, 2026; no public parameter count and no public price.
How it scores
- On LMArena Vision (style-controlled) it scores 1229 (CI 1219–1239), #76 of 193 (top 40%); 80 behind Claude Fable 5; level with Gemini 2.5 Flash Preview 09 2025 above and Qwen3.5 122B A10B is 3 below.
- On LMArena Text factuality it scores 1424 (CI 1420–1429), #142 of 215 (top 67%); 98 behind Gemini 4 Carbon; level with Gemini 2.5 Flash Preview 09 2025 above and level with Inkling 2 Small below.
- On LMArena Text (style-controlled, longer query) it scores 1417 (CI 1410–1424), #174 of 248 (top 71%); 123 behind Gemini 4 Argon; level with GLM 4.5 above and level with Gemini 2.5 Flash Preview 09 2025 below.
History
First result on isitsota: Nov 19, 2026. Best overall rank so far: #114 in Factuality, first held Nov 22, 2026.
The ruling, in plain English
Ranked #140 in General LLM.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) Gemini 2.5 Flash Preview (09-2025) | 1403 1399–1407 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, hard prompts) Gemini 2.5 Flash Preview (09-2025) | 1420 1415–1425 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, math) Gemini 2.5 Flash Preview (09-2025) | 1409 1396–1422 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, coding) Gemini 2.5 Flash Preview (09-2025) | 1428 1420–1435 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, longer query) Gemini 2.5 Flash Preview (09-2025) | 1417 1410–1424 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Vision (style-controlled) Gemini 2.5 Flash Preview (09-2025) | 1229 1219–1239 | 2026-11-19 | INDEP. | snap_71563b13a9cc |
| LMArena Text factuality Gemini 2.5 Flash Preview (09-2025) | 1424 1420–1429 | 2026-11-19 | INDEP. | snap_275d95909246 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| General LLM | #140 in this category | #140 | Gemini 4 Carbon |
| Reasoning | #142 in this category | #142 | Gemini 4 Carbon |
| Math | Not enough data | — | GPT-6 Astra |
| Coding | Not enough data | — | Claude Sonnet 5.5 |
| Long context | #132 in this category | #132 | Gemini 4 Argon |
| Vision | Not enough data | — | — |
| Factuality | #114 in this category | #114 | Gemini 4 Carbon |
Related pages
- General LLM
- Reasoning
- Math
- Coding
- Long context
- Vision
- Factuality
- LMArena Vision (style-controlled)
- LMArena Text (style-controlled, overall)
- LMArena Text (style-controlled, coding)
- LMArena Text (style-controlled, math)
- LMArena Text (style-controlled, hard prompts)
- LMArena Text (style-controlled, longer query)
- LMArena Text factuality
- Lab: Google DeepMind
Is Gemini 2.5 Flash Preview SOTA?
Best current rank: #114 in Factuality, as of Nov 22, 2026.
What is Gemini 2.5 Flash Preview best at?
As of Nov 22, 2026, Gemini 2.5 Flash Preview is ranked #114 in Factuality (since Nov 22, 2026; sources LMArena Text factuality).
How does Gemini 2.5 Flash Preview rank in Coding?
As of Nov 22, 2026, Gemini 2.5 Flash Preview is short of the evidence for a rank in Coding (since Nov 22, 2026; sources LMArena Text (style-controlled, coding); methodology v1.0).