Gemini 3.5 Flash-LitevsGLM-5.2
Gemini 3.5 Flash-Lite | GLM-5.2 | |
|---|---|---|
| Specifications | ||
Parameters | — | 744B |
Context window | — | 1M |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 31% |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 54.2% | 62.1%Best |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 54.6% |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | — | 44% |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 88% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 54% | 81%Best |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 49% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 40.5% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 54.7% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 91.2% |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 74% | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1140 | 1514Best |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1587 |
| Timeline | ||
| Release gap | GLM-5.2 shipped 35 days before Gemini 3.5 Flash-Lite | |
| Overview | ||
| Company | Z.ai | |
| Release date | Jul 21 2026 | Jun 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: Gemini 3.5 Flash-Lite or GLM-5.2?
GLM-5.2 leads Gemini 3.5 Flash-Lite on 3 of the 3 benchmarks they both report (SWE-Bench Pro, Terminal-Bench 2.1, GDPval-AA v2). GLM-5.2 shipped 35 days before Gemini 3.5 Flash-Lite, so benchmark comparisons should account for the intervening progress.
Gemini 3.5 Flash-Lite is proprietary, while GLM-5.2 is open weight.
On SWE-Bench Pro, GLM-5.2 leads at 62.1% vs Gemini 3.5 Flash-Lite at 54.2%. On Terminal-Bench 2.1, GLM-5.2 leads at 81% vs Gemini 3.5 Flash-Lite at 54%. On GDPval-AA v2, GLM-5.2 leads at 1514 vs Gemini 3.5 Flash-Lite at 1140.
Frequently asked questions
Gemini 3.5 Flash-Lite was released by Google on Jul 21 2026.
GLM-5.2 was released by Z.ai on Jun 16 2026.
GLM-5.2 leads on SWE-Bench Pro — Gemini 3.5 Flash-Lite 54.2% vs GLM-5.2 62.1%.
Gemini 3.5 Flash-Lite is a proprietary model released by Google. GLM-5.2 is an open weight model released by Z.ai.