modelgrep

Google: Gemini 3.5 Flash vs OpenAI: GPT-5.2-Codex

google logoGoogle: Gemini 3.5 Flashgoogle/gemini-3.5-flashVSopenai logoOpenAI: GPT-5.2-Codexopenai/gpt-5.2-codex

Google: Gemini 3.5 Flash wins on more metrics (9 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricGoogle: Gemini 3.5 FlashOpenAI: GPT-5.2-Codex
Intelligence Index50.2✓40.1
Coding Index70.1✓—
GPQA Diamond92%✓90%
Design Arena Elo1313✓—
Speed (tokens/sec)136✓64
Latency1.4s✓1.6s
Input price /M$1.50✓$1.75
Output price /M$9.00✓$14.00
Context window1.0M✓400K
CapabilitiesReasoningToolsJSONVisionAudioReasoningToolsJSONVision
Google: Gemini 3.5 Flash details →OpenAI: GPT-5.2-Codex details →