Gemini 3.6 Flash
AI models review
As of Aug 12, 2026, Gemini 3.6 Flash is rated 1483 Elo on LM Arena (13,481 Arena votes).
Is Gemini 3.6 Flash worth it in 2026?
Gemini 3.6 Flash sits at rank 15 of 20 in text Elo (1483) and rank 18 in coding Elo (1537) on LM Arena, placing it in the lower tier of the tracked models on both fronts. Its Artificial Analysis Intelligence Index is 51.6 and its Coding Index is 69.2, reflecting middling general ability with somewhat stronger coding scores. It does offer a very large context window of 1,048,576 tokens and a fast median output speed of 220 tokens per second. Pricing is 1.5 USD per 1M input tokens and 7.5 USD per 1M output tokens, which is not especially cheap given its competitive standing.
Long-document processing tasks that benefit from its massive context window, and workflows where fast output speed matters more than top-tier quality.
Its text and coding ranks are near the bottom of the tracked field (15 of 20 and 18 respectively), and the output price of 7.5 USD per 1M tokens is hard to justify given that performance level.
ReviewPond's conclusion, drawn only from the verified scores and review themes below. Not a paid or editorial opinion.
Benchmark and price facts
- Vendor
- License
- proprietary
- LM Arena text
- 1483 Elo (#15 of 20)
- LM Arena coding
- 1537 Elo (#18)
- Price (input)
- $1.5 / 1M tokens
- Price (output)
- $7.5 / 1M tokens
- Context window
- 1.048.576 tokens
- AA Intelligence Index
- 51.6 / 100
- AA Coding Index
- 69.2 / 100
- Output speed (AA)
- 220 tokens/s
- Human votes
- 13.481
Elo and votes from LM Arena; price and context from OpenRouter. Real fetched values, attributed, never blended.