Nano GPT logo
NanoGPT
Provider logo

GLM 4.6

z-ai/glm-4.6
BackTry Model
Provider logo

GLM 4.6

z-ai/glm-4.6
BackTry Model

Latest GLM series chat model with strong general performance. Quantized at FP8

Added Sep 30, 2025

Model weights

Context Window

200.0K

Max Output

65.5K

Avg output tokens (7d)

742 tokens

35%

Input Price (Auto)

$0.37/1M

Output Price (Auto)

$1.47/1M

Cache Read (Auto)

$0.18/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

23.0

Better than 65% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

63.2%

Better than 45% of models compared

HLE

Humanity's Last Exam

5.2%

Better than 40% of models compared

IFBench

Instruction-following benchmark

36.7%

Better than 31% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

76.9%

Better than 69% of models compared

AA-LCR

Long context reasoning evaluation

26.3%

Better than 41% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

SciCode

Python programming for scientific computing

33.1%

Better than 52% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

28.8%

Better than 72% of models compared

LiveCodeBench

Contamination-free coding benchmark

56.1%

Better than 63% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

44.3%

Better than 45% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

78.4%

Better than 60% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

21.4%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

67.6%

Last updated Jun 28, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare GLM 4.6 with similar models from the same provider or model family.

GLM 5V Turbo Thinking

z-ai/glm-5v-turbo:thinking

Thinking-enabled GLM 5V Turbo for image, video, and text inputs. Uses the same multimodal foundation model with more deliberate vision-grounded analysis, planning, and tool use. Not included in the subscription.

GLM 5V Turbo

z-ai/glm-5v-turbo

Z.ai's native multimodal agent model for vision-based coding and agent workflows. This is the standard non-thinking variant for image, video, and text inputs, tuned for perceive-plan-execute loops, complex coding, and tool-driven task execution. Not included in the subscription.

GLM 5 Turbo

z-ai/glm-5-turbo

Fast GLM 5 Turbo variant from Z-AI for general chat, coding, and tool use. Not included in the subscription.

GLM 4.5V

z-ai/glm-4.5v

Multimodal GLM 4.5V that handles images alongside text while keeping the balanced reasoning strength of the GLM 4.5 family.

GLM 4.5V Thinking

z-ai/glm-4.5v:thinking

Thinking-enabled GLM 4.5V that surfaces structured reasoning before its final answer. Great for image-grounded analysis, OCR, charts, and deliberate step-by-step responses.

GLM 4.6 Thinking

z-ai/glm-4.6:thinking

Thinking version of the latest GLM series chat model with strong general performance. Quantized at FP8