GLM-4-Plus
GLM-4-PlusCompare inon
Benchmarks of GLM-4-Plus14
BenchmarkByScoreRank
No benchmark matches
Rankingconfiguration unstated?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemini 4 Argonhighwins 76%-20%*$1.99Synchronous output stops at 65,536+2
BetterGPT-6 Lunamaxwins 63%-96%$0.068Function calling only with none · Chat Completions+3
OpenKimi K3maxwins 70%+20%$2.00Sampling parameters are fixed+3CheaperGemini 3.8 Flashhighwins 73%-70%*$1.24Sampling parameters are ignored+1CheaperGemini 3.1 Pro Previewunstatedwins 72%-10%$2 / $12Cannot use both thinking controlsModelScoreCostPer taskWhat changes
Gemini 4 Argonhighwins 76%-20%*$1.99Synchronous output stops at 65,536+2Gemini 3.8 Flashhighwins 73%-70%*$1.24Sampling parameters are ignored+1Gemini 3.1 Pro Previewunstatedwins 72%-10%$2 / $12Cannot use both thinking controlsGemini 3.6 Flashhighwins 71%-70%*$1.60
Muse Sparkunstatedwins 70%-60%$1.25 / $4.25Only n=1 · Meta / Chat Completions+1ModelScoreCostPer taskWhat changes
GPT-6 Lunamaxwins 63%-96%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 63%-91%$0.085GPT-5.6 Terraxhighwins 66%-10%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 69%-20%$0.72Remove unsupported parameters+5Muse Spark 1.2xhighwins 68%-60%$0.97Only auto tool_choice is supported+1ModelScoreCostPer taskWhat changes
Kimi K3maxOpenwins 70%+20%$2.00Sampling parameters are fixed+3GLM 5.2maxOpenwins 69%-57%$1.47GLM 5.3maxOpenwins 69%-57%$2.01Reasoning cannot be disabled+3GLM 5unstatedOpenwins 68%-69%$1 / $3.20GLM 5.1unstatedOpenwins 68%-57%$1.40 / $4.40ModelScoreCostPer taskWhat changes
GLM 5.2maxOpenwins 69%—$1.47GLM 5.3maxOpenwins 69%—$2.01Reasoning cannot be disabled+3GLM 5unstatedOpenwins 68%—$1 / $3.20GLM 5.1unstatedOpenwins 68%—$1.40 / $4.40GLM 5.3 FlashunstatedOpenwins 66%—$0.15 / $0.50Defaults to max · Self-hosted+4GLM 5V Turbounstatedwins 63%—$1.20 / $4GLM 4.7unstatedOpenwins 63%—$0.60 / $2.20GLM 4.5unstatedOpenwins 58%—$0.60 / $2.20All Z.ai models →Benchmarks
all categoriesChat & Knowledge
Arena Text · overall1,343#128
Writing & Language
Arena Text · creative writing1,316#118
FAQ
How much does GLM-4-Plus cost?›
$5 per 1M input tokens and $5 per 1M output tokens; cached input $2.50 per 1M.
Is GLM-4-Plus free to use?›
There is no free API; the cheapest paid price is $5 per 1M input tokens.
How good is GLM-4-Plus, and what is it best at?›
#128 of 196 in Chat & Knowledge, #118 of 195 in Writing & Language.
Is GLM-4-Plus better than Qwen Plus?›
On Arena Text · creative writing, GLM-4-Plus scores 1,316 vs 1,316 — about the same.
How can I use GLM-4-Plus?›
Through the Z.ai API.
What is the context window of GLM-4-Plus?›
128K tokens.
Can GLM-4-Plus read images?›
No, it accepts text only.
What is GLM-4-Plus?›
GLM-4-Plus is a language model from Z.ai.
What are the best alternatives to GLM-4-Plus?›
Gemini 4 Argon (cheaper), GPT-6 Luna (better), Kimi K3 (open weights).