How much does GLM-5.3 cost?

GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens, using the list price from Zai as of 26 Oct 2026. That is about $0.36 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.

What is the context window of GLM-5.3?

GLM-5.3 has a context window of 1M tokens, roughly 750,000 words of text read at once. A single answer can be up to 128K tokens long.

Is GLM-5.3 open source?

GLM-5.3 has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.

How good is GLM-5.3 compared with other AI models?

On the Epoch Capabilities Index, GLM-5.3 scores 156.0 (likely range 154.2 to 158.3), which ranks 31 of 270 models we track. On Arena's human-vote text board it is ranked 23 of 166. Scores close together are a tie in practice.

How does GLM-5.3 compare with Muse Spark 1.1?

GLM-5.3 scores higher on 2 of 6 shared quality measures, Muse Spark 1.1 on 1. 3 measures are too close to call. Their blended prices are similar ($2.15 and $2.00 per million tokens). See the full comparison for every measure.

How current are these numbers for GLM-5.3?

The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

AI Rankings

GLM-5.3: Score, Price and Context Window

Where GLM-5.3 from Z.ai ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

Z.ai
Open weights
Released Aug 2026

Its score range overlaps with GPT-5.2 Pro, the model just above it, so a small gap in rank is not a meaningful difference.

Best for

Very long documents: its context window is 1M tokens, roughly 750,000 words.
Running it yourself: its weights can be downloaded (read the licence terms first).

These lines are worked out from the numbers on this page, not from hands-on testing.

Key facts

Overall score: 156.0; Rank 31 of 270. Likely range 154.2 to 158.3.
Human preference: chat: 1481; Rank 23 of 166. 25,144 votes, at the "Max" setting.
Human preference: coding: 1521; Rank 28 of 166. 5,965 votes, at the "Max" setting.
Human preference: web pages: 1623; Rank 17 of 85. 10,315 votes, at the "Max" setting.
Price per million tokens: $1.40 in / $4.40 out; Blended $2.15. Cached input $0.26. List price from Zai, checked 26 Oct 2026.
Context window: 1M tokens; About 750,000 words at once. One answer up to 128K tokens.
Weights: Open; The weights can be downloaded. Check the licence before commercial use.

Features listed by the price list: Tool use, Reasoning, Prompt caching.

How GLM-5.3 stacks up

Each strip shows every model we track as faint bars. The dot is this model. Better is always to the right, even for price.

GLM-5.3 compared with all models we trackOverall capability: 156.0. Better than 88% of the other 269 models. Human preference: chat: 1481. Better than 86% of the other 165 models. Human preference: coding: 1521. Better than 83% of the other 165 models. Human preference: web pages: 1623. Better than 80% of the other 84 models. Price: $2.15 per 1M. Cheaper than 34% of the other 200 priced models. Context window: 1M tokens. Larger context window than 72% of the other 198 models.

Overall capability156.0
Better than 88% of the other 269 modelsTop 25%
Epoch Capabilities Index: one score that combines many tests.
Human preference: chat1481
Better than 86% of the other 165 modelsTop 25%
How often people pick its answers over another model's on Arena.
Human preference: coding1521
Better than 83% of the other 165 modelsTop 25%
How often people pick its answers to coding questions on Arena.
Human preference: web pages1623
Better than 80% of the other 84 modelsTop 25%
How often people pick the web pages and small apps it builds on Arena.
Price$2.15 per 1M
Cheaper than 34% of the other 200 priced models
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window1M tokens
Larger context window than 72% of the other 198 modelsUpper half
How much text it can read at once. Bigger suits long documents.

Compared with the other published models that have each measure. Data updated 26 Oct 2026.

Where GLM-5.3 ranks

Leaderboards it appears on, best placing first.

See all leaderboards

Test results

Each test checks one kind of skill. Place shows where it stands among the models that took that test.

GPQA Diamond
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
90.9%
Place 31 of 183
tied with 3 others
DeepSWE
Software engineering tasks scored as the share solved on the first try (pass@1), run with the open mini-SWE-agent setup.
69.0%
Place 7 of 26
OTIS Mock AIME
Maths competition problems in the style of the US AIME exam, from the 2024 and 2025 sets. Every answer is a whole number.
91.1%
Place 55 of 174
tied with 2 others
FrontierMath (Tiers 1-3)
Original, very hard maths problems written by mathematicians. Each has an exact answer and the problems are kept private so models cannot have memorised them. This is the Tiers 1 to 3 set, version 2.
68.8%
Place 28 of 87
SimpleQA Verified
Short factual questions that each have one correct answer. It measures how often a model gets facts right.
41.0%
Place 46 of 82
tied with 1 other

What it costs in everyday terms

List prices turned into amounts you can picture. Real bills depend on how you use it.

100 chats: $0.36; Cost of 100 chats assumes each chat sends 1,000 tokens (about 750 words) and gets 500 tokens (about 375 words) back.
A 300-page book: $0.14; Cost to read a 300-page book assumes about 100,000 input tokens and no reply. A real book varies with page size and language.
Blended price: $2.15 per 1M; Three parts input to one part output. Our own calculation for comparing models.

Compare GLM-5.3

Side-by-side pages for the closest rivals.

Similar models

Learn more

Questions about GLM-5.3

How much does GLM-5.3 cost?: GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens, using the list price from Zai as of 26 Oct 2026. That is about $0.36 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.
What is the context window of GLM-5.3?: GLM-5.3 has a context window of 1M tokens, roughly 750,000 words of text read at once. A single answer can be up to 128K tokens long.
Is GLM-5.3 open source?: GLM-5.3 has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.
How good is GLM-5.3 compared with other AI models?: On the Epoch Capabilities Index, GLM-5.3 scores 156.0 (likely range 154.2 to 158.3), which ranks 31 of 270 models we track. On Arena's human-vote text board it is ranked 23 of 166. Scores close together are a tie in practice.
How does GLM-5.3 compare with Muse Spark 1.1?: GLM-5.3 scores higher on 2 of 6 shared quality measures, Muse Spark 1.1 on 1. 3 measures are too close to call. Their blended prices are similar ($2.15 and $2.00 per million tokens). See the full comparison for every measure.
How current are these numbers for GLM-5.3?: The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

Where this data comes from

Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
Arena (formerly LMArena): Human-preference ratings: Arena (arena.ai) leaderboard dataset, CC BY 4.0. We keep the latest published ratings, match them to models from other sources and rank them. Ratings are not changed. Arena does not endorse this site.
LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.

Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake