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)	41.2	330.576
Gemini 3.8 Flash (medium)	40	0
Gemini 3.7 Flash (medium)	39.6	353.43
Gemini 3.7 Flash (high)	39.4	333.342
Gemini 3.7 Flash (low)	36.9	305.594
Gemini 3.6 Flash (high)	34.3	201.728
Gemini 3.8 Flash (low)	33.8	0
Gemini 3.5 Flash (medium)	33.6	256.037
Gemini 3.5 Flash (high)	33	0
Gemini 3.1 Pro Preview	30.4	125.029
Gemini 3 Pro Preview (high)	28	0
Gemini 3 Flash Preview (Reasoning)	26.3	0
Gemini 3.5 Flash (minimal)	23.8	240.075
Gemini 3.5 Flash-Lite	22.7	349.946
Gemini 3 Pro Preview (low)	22.3	0
Gemini 3 Flash Preview (Non-reasoning)	17.9	0
Gemma 4 26B A4B (Reasoning)	16.7	0
Gemini 2.5 Pro	16.7	0
Gemini 3.1 Flash-Lite	16	0
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	15.5	0
Gemma 4 31B (Reasoning)	15.4	34.573
Gemini 2.5 Pro Preview (Mar' 25)	15	0
Gemini 2.5 Pro Preview (May' 25)	14.5	0
Gemma 4 12B (Reasoning)	14.2	133.963
Gemma 4 31B (Non-reasoning)	13.9	42.981
Gemma 4 26B A4B (Non-reasoning)	13.1	96.409
Gemini 2.5 Flash (Reasoning)	13.1	0
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	12.4	0
Gemini 2.5 Flash Preview (Reasoning)	11.7	0
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	10.4	0
Gemini 2.5 Flash (Non-reasoning)	9.9	0
DiffusionGemma 26B A4B	9.5	0
Gemma 4 12B (Non-reasoning)	9.4	134.714
Gemini 2.0 Flash Thinking Experimental (Jan '25)	9.4	0
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	9.3	0
Gemma 4 E4B (Reasoning)	8.9	41.149
Gemini 2.0 Flash (Feb '25)	8.9	0
Gemini 2.0 Pro Experimental (Feb '25)	8.7	0
Gemini 2.5 Flash Preview (Non-reasoning)	8.7	0
Gemini 2.5 Flash-Lite (Reasoning)	8.5	0

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