# LLM Duel: Gemini 3 Flash vs Opus 4.5 vs GPT-5.2-Codex vs GLM-4.7

DevFeed: [LLM Duel: Gemini 3 Flash vs Opus 4.5 vs GPT-5.2-Codex vs GLM-4.7](<https://devfeed.tech/articles/llm-duel-gemini-3-flash-vs-opus-4-5-vs-gpt-5-2-codex-vs-glm-4-7-27199.md>)

Original publisher: [Read original article](<https://antonioleiva.com/llm-duel-gemini-opus-gpt-glm>)

Published: 2025-12-23T00:00:00Z

Content type: comparison

Language: en

Sources: [Antonio Leiva](<https://devfeed.tech/sources/antonio-leiva.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [codex](<https://devfeed.tech/topics/codex.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [codex](<https://devfeed.tech/tags/codex.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [llm](<https://devfeed.tech/tags/llm.md>), [qwen](<https://devfeed.tech/tags/qwen.md>)

## AI overview

The article compares Gemini 3 Flash, Opus 4.5, GPT-5.2-Codex, and GLM-4.7 through a practical coding project: building an image editor for YouTube thumbnails. It evaluates not only code generation but also task planning and preliminary research, while questioning how well benchmarks reflect real-world use.

## Source excerpt

Everything Android, Kotlin and other random topics