Inference
EN
Z.AI

GLM-5V-Turbo

GLM-5V-Turbo is a standard model from Z.AI in the GLM-5 family. 10 benchmarks count toward its index, in 5 categories.

  • Closed weights
  • Standard
  • Input: image · text · video
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.48.1±8.6Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.30/sMedian 67/s
First tokenSeconds to the first output token.3.3 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.20Median $0.60
Output / 1MUS dollars per 1M output tokens.$4.00Median $2.55
ContextMaximum tokens in one request.203KMedian 262K
EloLMArena rating and rank.1438±6 #82Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
z-ai/glm-5v-turbo
Max outputMaximum output tokens per request.
131K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
No
Cache read / 1MUS dollars per 1M cached tokens.
$0.24
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
4 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
Zhipu AIMaker$0.747$3.29200K
OpenRouterRouter$1.20$4.00203K
SiliconFlowHost$1.20$4.00200K
Z.AIMaker$1.20$4.00200K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted50.5125 / 218
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.2 counted46.8138 / 227
MultimodalTasks with images and text.1 counted49.9—
KnowledgeFacts and expert knowledge.3 counted46.9158 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted46.1—
MathMath problems.None counted——

Results

10 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
τ²-Bench Tool-Agent-User EvaluationAgenticAbove fitFar above this model's index.98.5%3 / 149
Artificial Analysis IFBenchInstruction61.1%62 / 146
Artificial Analysis GPQA DiamondKnowledge80.9%97 / 199
Artificial Analysis Omniscience AccuracyKnowledge29.3%80 / 164
Artificial Analysis Long Context ReasoningReasoning70.3%112 / 217
Artificial Analysis Humanity's Last ExamKnowledge17.1%121 / 222
Artificial Analysis MMMU-ProMultimodal72.8%67 / 113
Critical Physics TasksReasoning0.6%132 / 214
Claw-EvalAgentic53.8%36 / 42
Gert Labs Composite Game BenchmarkAgentic30.8%48 / 52

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reusemodels.devMIT

History

5 releases
Index49.0 → 48.1
23 Oct 202612 Nov 2026
Output / 1M$4.00 → $4.00
23 Oct 202612 Nov 2026

Questions

How much does GLM-5V-Turbo cost?
$1.20 per 1M input tokens, $4.00 per 1M output tokens.
How good is GLM-5V-Turbo?
Its index is 48.1 out of 100. That is place 160 of 283 ranked models.
What is GLM-5V-Turbo best at?
Agentic: 50.5 out of 100, place 125 of 218.
How fast is GLM-5V-Turbo?
30 output tokens per second, 3.3 s to the first token.
What is the context window of GLM-5V-Turbo?
203K tokens.
Is GLM-5V-Turbo open source?
No. Its weights are not published.
When was GLM-5V-Turbo released?
April 2026.

Badge

GLM-5V-Turbo on Inference360: place 160 of 283, index 48.1
HTML
<a href="https://inference360.ai/models/glm-5v-turbo"><img src="https://inference360.ai/badges/glm-5v-turbo.svg" alt="GLM-5V-Turbo on Inference360: place 160 of 283, index 48.1" height="20"></a>
Markdown
[![GLM-5V-Turbo on Inference360: place 160 of 283, index 48.1](https://inference360.ai/badges/glm-5v-turbo.svg)](https://inference360.ai/models/glm-5v-turbo)

Compare with

Gemma 4 31B47.9GLM-5-Turbo51.9GLM-5.156.0

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Z.AI

All models
GLM-5.156.0GLM-5-Turbo51.9GLM-551.6GLM-5 (Reasoning)UnrankedGLM-4.7-FlashUnranked