NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 5.3 Flash
z-ai logo

GLM 5.3 Flash

by z-ai · Released Aug 2026

Multimodal1M Context
48.9
avg score
Rank #152
Compare
Better than 51% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.15
Output $/1M
$0.50
Type
multimodal
License
Proprietary
Benchmarks
20 tested
Data as of
About

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Tested on 20 benchmarks · BenchGecko score 48.9. Top scores: Chatbot Arena Elo — Coding (1615.6%), Chatbot Arena Elo — Overall (1473.0%), OTIS Mock AIME 2024-2025 (93.9%).

Looking for similar performance at lower cost?
Phi 4 scores 49.0 (100% as good) at $0.07/1M input · 53% cheaper
Capabilities
coding
47.6
#102 globally
math
55.6
#99 globally
knowledge
48.2
#138 globally
agentic
52.8
#17 globally
general
24.5
#146 globally
speed
53.9
#22 globally
Benchmark Scores
Compare All
Tested on 20 benchmarks · Ranked across 7 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Deepswe
63.4·
Frontiercode
31.8·
mathCompare math →
OTIS Mock AIME 2024-2025

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

93.9·
FrontierMath-Tiers-1-3-v2-Private
55.8·
FrontierMath-Tier-4-v2-Private
17.1·
knowledgeCompare knowledge →
GPQA diamond

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

86.9·
Chess Puzzles

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

9.5·
Quick compare:Microsoft logovs Phi 4OpenAI logovs GPT-5 ProAlibaba Qwen logovs Qwen3 Max
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · z-ai GLM 5.3
Aug 2026
63.1
$1.40/M in1.0Mctx22 benchmarks
Aug 2026
$0.45/M in(-0.95)1.0Mctx
Aug 2026
48.9-14.2
$0.15/M in(-0.30)1.0Mctx20 benchmarks
Aug 2026
$0.06/M in(-0.09)1.0Mctx
Sep 2026
$0.37/M in(+0.31)1.0Mctx
Sep 2026
$2.80/M in(+2.43)1.0Mctx(-49K)
See the full GLM 5.3 family →
Recently Happened
GLM 5.3 Flash pricing increased 257%
Sep 28, 2026
GLM 5.3 Flash pricing increased 67%
Sep 22, 2026
GLM 5.3 Flash pricing dropped 10%
Sep 17, 2026
GLM 5.3 Flash pricing increased 114%
Sep 11, 2026
GLM 5.3 Flash added
Aug 27, 2026
Similar Models
Microsoft logo
Phi 4
Microsoft
49.0$0.07/1M
OpenAI logo
GPT-5 Pro
OpenAI
48.7$15.00/1M
Alibaba Qwen logo
Qwen3 Max
Alibaba Qwen
49.2$0.78/1M
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
BenchGecko API
glm-5-3-flash
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedAug 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.001
Available On
z-ai logoz-ai$0.15
Categories
codingmathknowledgeagenticgeneralspeed
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Microsoft logoPhi 4
49.0
OpenAI logoGPT-5 Pro
48.7
Alibaba Qwen logoQwen3 Max
49.2
Alibaba Qwen logoQwen3 Next 80B A3B Instruct
49.2
GLM 5.3 Flash is a proprietary multimodal AI model by z-ai, released in August 2026. It has an average benchmark score of 48.9. Context window: 1M tokens.

Related Models

Phi 4 · MicrosoftGPT-5 Pro · OpenAIQwen3 Max · Alibaba QwenQwen3 Next 80B A3B Instruct · Alibaba QwenClaude 3.7 Sonnet · Anthropic

Benchmarks

Chatbot Arena Elo — CodingChatbot Arena Elo — OverallOTIS Mock AIME 2024-2025Artificial Analysis · GPQA DiamondGPQA diamond

Related Pages

z-ai · Providerz-ai · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • GLM 5.3 Flash by z-ai. BenchGecko score 48.9, rank 152 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.15 input · $0.50 output per 1M tokens (as of 2026-10-05).
  • Sold by 32 providers (as of 2026-10-05): Relace $0.0352 in / $0.50 out · InferenceNet (fp4) $0.0440 in / $0.60 out · Sail Research (fp4) $0.0450 in / $0.60 out · OpenInference (fp4) $0.0458 in / $0.65 out · Wafer $0.0500 in / $0.50 out · and 27 more. Every provider
  • Gecko Tests · Gecko Score 39 (rank 9): Who Are You B (Knows who made it) · World Map D (89.7% of the map right) · Tokenizer Tax D (70% more tokens outside English).

How to cite · data as of 2026-10-05

GLM 5.3 Flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-5-3-flash

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