Google cloud models

65 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.

Model	Intelligence	Speed (tok/s)
Gemini 3.8 Flash (high)	47.1	339.975
Gemini 3.8 Flash (medium)	46.8	391.997
Gemini 3.7 Flash (high)	45.2	284.382
Gemini 3.7 Flash (medium)	43.4	294.255
Gemini 3.8 Flash (low)	42.4	288.457
Gemini 3.7 Flash (low)	41.1	286.335
Gemini 3.6 Flash (high)	40.3	185.655
Gemini 3.5 Flash (high)	39.7	0
Gemini 3.5 Flash (medium)	38	236.241
Gemini 3.1 Pro Preview	36.7	117.358
Gemini 3 Pro Preview (high)	32.4	0
Gemini 3 Flash Preview (Reasoning)	30.7	0
Gemini 3.5 Flash (minimal)	28	219.063
Gemini 3.5 Flash-Lite	27.6	315.484
Gemini 3 Pro Preview (low)	26.3	0
Gemma 4 31B (Reasoning)	22.2	35.058
Gemini 3 Flash Preview (Non-reasoning)	20.8	0
Gemma 4 26B A4B (Reasoning)	19.2	0
Gemini 2.5 Pro	19	0
Gemini 3.1 Flash-Lite	18.7	0
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	17.4	0
Gemini 2.5 Pro Preview (Mar' 25)	16.7	0
Gemini 2.5 Pro Preview (May' 25)	16.1	0
Gemma 4 12B (Reasoning)	15.6	129.767
Gemma 4 31B (Non-reasoning)	15.2	66.794
Gemma 4 26B A4B (Non-reasoning)	13.9	88.01
Gemini 2.5 Flash (Reasoning)	13.9	0
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	12.7	0
Gemini 2.5 Flash Preview (Reasoning)	11.5	0
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	9.2	0
Gemini 2.5 Flash (Non-reasoning)	8.2	0
DiffusionGemma 26B A4B	7.6	0
Gemini 2.0 Flash Thinking Experimental (Jan '25)	7.4	0
Gemma 4 12B (Non-reasoning)	7.3	127.991
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	7.3	0
Gemini 2.0 Flash (Feb '25)	6.5	0
Gemma 4 E4B (Reasoning)	6.4	37.229
Gemini 2.0 Pro Experimental (Feb '25)	6.1	0
Gemini 2.5 Flash Preview (Non-reasoning)	5.9	0
Gemini 2.5 Flash-Lite (Reasoning)	5.6	0

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.