GLM-5
The fifth-generation large language model in the GLM series, released by Zhipu AI, designed for multi-task reasoning and content generation.
Core Facts
Timeline (last 90 days)
The benchmark covers 9 models from 6 labs, including Qwen3 235B, Claude Haiku 4.5, Claude Opus 5.5, Gemini series, GPT-5.4 series, GLM-5, and Grok 4.20, of which 4 are reasoning models.
GLM-5揪出了作者早期A02提示词的歧义——收货并不等于消耗，作者据此修正了题目
Zhipu's GLM-5 identified itself as Gemini made by Google in a Spanish-language scenario, and after being misled by a suggestive question, identified itself as Claude made by Anthropic.
Open-source models scored lower: Qwen3 235B scored 11/12, both sizes of Gemma 4 scored 9/12, DeepSeek R1 scored 7/12, and GLM-5 scored 5/12.
In the ng-hard stress test, Gemini 3.7 Flash, GLM-5, and Qwen 3 235B all scored 100%, while gpt-oss-120b scored 80% (8 out of 10 rows).
The models tested include Google's Gemini 3.7 Flash, Z.ai's GLM-5, Alibaba's Qwen 3 235B A22B Instruct, and OpenAI's gpt-oss-120b, all running on Kaggle.
After correcting the scorer, all four models achieved 100% on all five Sanity gate tasks.
Among the three perfect-scoring models, the cost of GLM-5 is approximately 30 times that of Qwen.
GLM-5 and Gemini 2.5 Pro tied for second place, both scoring 0.92 (34/37).
For equivalent intelligent tasks, the weighted average cost of Gemini 3.8 Flash is approximately $0.58, while some comparison models cost $2.34 or even $3.69.
2 more timeline events
All Facts (11)
The models tested include Google's Gemini 3.7 Flash, Z.ai's GLM-5, Alibaba's Qwen 3 235B A22B Instruct, and OpenAI's gpt-oss-120b, all running on Kaggle.
65%UnverifiedThe benchmark covers 9 models from 6 labs, including Qwen3 235B, Claude Haiku 4.5, Claude Opus 5.5, Gemini series, GPT-5.4 series, GLM-5, and Grok 4.20, of which 4 are reasoning models.
50%UnverifiedZhipu's GLM-5 identified itself as Gemini made by Google in a Spanish-language scenario, and after being misled by a suggestive question, identified itself as Claude made by Anthropic.
50%UnverifiedOpen-source models scored lower: Qwen3 235B scored 11/12, both sizes of Gemma 4 scored 9/12, DeepSeek R1 scored 7/12, and GLM-5 scored 5/12.
50%UnverifiedIn the ng-hard stress test, Gemini 3.7 Flash, GLM-5, and Qwen 3 235B all scored 100%, while gpt-oss-120b scored 80% (8 out of 10 rows).
50%UnverifiedAfter correcting the scorer, all four models achieved 100% on all five Sanity gate tasks.
50%UnverifiedAmong the three perfect-scoring models, the cost of GLM-5 is approximately 30 times that of Qwen.
50%UnverifiedGLM-5 and Gemini 2.5 Pro tied for second place, both scoring 0.92 (34/37).
50%UnverifiedThe GLM-5 series strengthens long-text processing (supporting 128K context) and tool-calling (Function Calling) capabilities.
50%UnverifiedThe GLM-5 series supports a 128K context length and Function Calling tool invocation capability.
50%UnverifiedGLM-5揪出了作者早期A02提示词的歧义——收货并不等于消耗，作者据此修正了题目
50%