Home/Models/GLM 5.3
z-ai logo

GLM 5.3

by z-ai · Released Aug 2026

1M Context
63.0
avg score
Rank #72
Compare
Better than 78% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.07
Output $/1M
$1.40
Type
text
License
Proprietary
Benchmarks
22 tested
Data as of
About

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

Tested on 22 benchmarks · BenchGecko score 63.0. Top scores: Artificial Analysis · GPQA Diamond (91.7%), GPQA diamond (91.5%), OTIS Mock AIME 2024-2025 (91.1%).

Capabilities
coding
53.7
#78 globally
math
64.3
#81 globally
knowledge
55.4
#98 globally
agentic
56.6
#17 globally
general
55.0
#28 globally
speed
56.3
#17 globally
Benchmark Scores
Compare All
Tested on 22 benchmarks · Ranked across 6 categories
Score Distribution (all 326 models)
0255075100
▲ You are here
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

75.4·
69.0·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

91.1·
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

91.5·
SimpleQA Verified

Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.

41.0·
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

33.7·
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Recently Happened
GLM 5.3 pricing dropped 71%
Oct 20, 2026
GLM 5.3 pricing increased 163%
Oct 16, 2026
GLM 5.3 added
Aug 19, 2026
Links
Documentation
Community
BenchGecko API
glm-5-3
Specifications
  • Typetext
  • Context1.0M tokens (~524 books)
  • ReleasedAug 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.002
Available On
z-ai logoz-ai$0.07
Share & Export
Tweet
GLM 5.3 is a proprietary text AI model by z-ai, released in August 2026. It has an average benchmark score of 63.0. Context window: 1M tokens.

Key facts · as of 2026-11-11

  • GLM 5.3 by z-ai. BenchGecko score 63.0, rank 72 of 326 scored models (normalized average of public benchmark scores).
  • List price $0.0699 input · $1.40 output per 1M tokens (as of 2026-11-11).
  • Sold by 45 providers (as of 2026-11-11): Wafer (fp4) $0.0699 in / $1.40 out · Relace (fp4) $0.0703 in / $4.38 out · InferenceNet (fp4) $0.0800 in / $3.60 out · InferenceNet (fp4) $0.0800 in / $3.60 out · Reka $0.15 in / $3.00 out · and 40 more. Every provider
  • Gecko Tests · Gecko Score 47 (rank 34): Who Are You B (Knows who made it) · Censorship Index C (Answers almost everything) · Knowledge Horizon C (Knows news up to Dec 2025) · Tokenizer Tax E (90% more tokens outside English).

How to cite · data as of 2026-11-11

GLM 5.3 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/glm-5-3

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP