Qwen2.5-CodervsGLM-5.1
Qwen2.5-Coder | GLM-5.1 | |
|---|---|---|
| Specifications | ||
Parameters | 32B | 744B |
Context window | 128k | 200k |
| 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. | — | 22% |
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. | — | 75% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 63.5% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 68% |
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. | — | 52.3% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86.2% |
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. | — | 1518 |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Nov 12 2024 | Apr 7 2026 |
| Access | Open Weight | Open Weight |
Which is better: Qwen2.5-Coder or GLM-5.1?
Qwen2.5-Coder and GLM-5.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Coder shipped 511 days before GLM-5.1, so benchmark comparisons should account for the intervening progress.
Qwen2.5-Coder has 32B parameters, while GLM-5.1 has 744B. Context windows are 128k (Qwen2.5-Coder) vs 200k (GLM-5.1).
Direct benchmark comparisons are unavailable — Qwen2.5-Coder and GLM-5.1 don't publish scores on any of the same benchmarks.
Frequently asked questions
Qwen2.5-Coder was released by Qwen on Nov 12 2024.
GLM-5.1 was released by Z.ai on Apr 7 2026.
Qwen2.5-Coder has a 128k context window; GLM-5.1 has 200k.
Other comparisons
Qwen2.5-CodervsClaude Opus 5GLM-5.1vsClaude Opus 5Qwen2.5-CodervsGPT-5.6 SolGLM-5.1vsGPT-5.6 SolQwen2.5-CodervsGemini 3.6 FlashGLM-5.1vsGemini 3.6 FlashQwen2.5-CodervsMuse Spark 1.1GLM-5.1vsMuse Spark 1.1Qwen2.5-CodervsGrok 4.5GLM-5.1vsGrok 4.5Qwen2.5-CodervsDeepSeek-V4-Flash-0731GLM-5.1vsDeepSeek-V4-Flash-0731