BroadRouter

GLM 5.3 API pricing

Updated

Among the 24 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for GLM 5.3 is DeepInfra (promotional) at USD 0.5625 per 1M input tokens and USD 2.50 per 1M output tokens. The median across 24 standard prices is USD 1.40 / USD 4.40. Z.ai's own API charges USD 1.40 / USD 4.40.

Z.ai · slug glm-5.3 · up to 1,048,576 tokens of context · 24 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-09-02 (3 archived price points, 0 list-price changes): LLM API price history.

What does Z.ai charge for GLM 5.3?

Input
USD 1.40
Cached input
USD 0.26
Output
USD 4.40
Blended 3:1
USD 2.15

USD per 1M tokens on Z.ai, model GLM-5.3, standard tier. Source, checked 2026-11-14.

Is a host cheaper than Z.ai? Yes. DeepInfra charges USD 0.5625 input and USD 2.50 output per 1M tokens, 51% below Z.ai's own USD 1.40 / USD 4.40 on the 3:1 blend (a promotional price).

GLM 5.3 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 4.1× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

GLM 5.3 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest promo
zai-org/GLM-5.3
Notes and source quote

Promotional price, 38% off list (list 0.9 in / 4.0 out).

“$0.563 in $2.50 out $0.125 cached / 1M tokens”
USD 0.5625USD 0.125USD 2.50USD 1.0471,048,576FP4DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2GMI Cloud promo
zai-org/GLM-5.3
Notes and source quote

Promotional price, 50% off list (list 1.4 in / 4.4 out / 0.26 cached).

“Price (per 1M tokens) 50% off Input $0.70 $1.40 Output $2.20 $4.40 Cache Read $0.13 $0.26 Cache Write -”
USD 0.70USD 0.13USD 2.20USD 1.0751,048,576FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
3AkashML promo
zai-org/GLM-5.3
Notes and source quote

Labelled "Limited Trial" on AkashML.

“Price (per 1M Tokens) Input Output Cache Read GLM 5.3 $0.19 $4.40 $0.19”
USD 0.19USD 0.19USD 4.40USD 1.2431,048,576not statedAkashML page
checked 2026-11-15
re-checked 2026-11-16
4Chutes
zai-org/GLM-5.3
Notes and source quote
“GLM-5.3 zai-org/GLM-5.3 $0.245 per 1M tokens $1.225 per 1M tokens $3.85 per 1M tokens 1.0M”
USD 1.225USD 0.245USD 3.85USD 1.8811,048,576not statedChutes page
checked 2026-11-15
re-checked 2026-11-16
5FriendliAI promo
zai-org/GLM-5.3
Notes and source quote

Promotional price, 10% off list (list 1.4 in / 0.26 cached / 4.4 out).

“10% OFF Input $1.26 $1.4 / 1M tokens Cached Input $0.234 $0.26 / 1M tokens Output $3.96 $4.4”
USD 1.26USD 0.234USD 3.96USD 1.9351,048,576not statedFriendliAI page
checked 2026-11-15
re-checked 2026-11-16
6Z.ai maker
GLM-5.3
Notes and source quote
“| GLM-5.3 | $1.4 | $0.26 | Limited-time Free | $4.4 |”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedZ.ai page
checked 2026-11-14
re-checked 2026-11-16
7Alibaba Cloud
glm-5.3
Notes and source quote

International (Singapore) deployment. Deployed by Alibaba Cloud Model Studio. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope.

“glm-5.3 International Non-Thinking and Thinking modes flat-rate pricing $1.400 $4.400”
USD 1.40USD 0.28USD 4.40USD 2.15not statednot statedAlibaba Cloud page
checked 2026-11-14
re-checked 2026-11-16
8Baseten
zai-org/GLM-5.3
Notes and source quote
“GLM-5.3 $1.40 $0.14 $4.40”
USD 1.40USD 0.14USD 4.40USD 2.15not statednot statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
9Cloudflare Workers AI
@cf/zai-org/glm-5.3
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/zai-org/glm-5.3 $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
10Crusoe Cloud
zai-org/GLM-5.3
Notes and source quote
“GLM-5.3 $1.40 $4.40 $0.26”
USD 1.40USD 0.26USD 4.40USD 2.151,048,576not statedCrusoe Cloud page
checked 2026-11-15
re-checked 2026-11-16
11DigitalOcean
Notes and source quote

DigitalOcean-hosted.

“GLM-5.3 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.40$4.40$0.26”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
12Featherless
zai-org/GLM-5.3
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $1.4 / CACHED $0.26 / OUTPUT $4.4”
USD 1.40USD 0.26USD 4.40USD 2.15262,144FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
13Fireworks AI
accounts/fireworks/models/glm-5p3
Notes and source quote
“GLM 5.3 | $1.40 / $0.26 / $4.40 | $1.75 / $0.325 / $5.50”
USD 1.40USD 0.26USD 4.40USD 2.151,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
14Hyperbolic
glm-5.3
Notes and source quote

Context shown on page as "1M" (rounded); stored as the decimal value.

“GLM 5.3 glm-5.3 Z.ai · 1M context · Text $1.40 $4.40 $0.26”
USD 1.40USD 0.26USD 4.40USD 2.151,000,000not statedHyperbolic page
checked 2026-11-14
re-checked 2026-11-16
15Mistral AI
zai-glm-5-3
Notes and source quote

Third-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Context from the docs model card.

“Z.ai GLM 5.3 ↗ $1.4 $0.14 $4.4”
USD 1.40USD 0.14USD 4.40USD 2.151,048,576not statedMistral AI page
checked 2026-11-14
re-checked 2026-11-16
16Novita AI
zai-org/glm-5.3
Notes and source quote
“GLM 5.3 1M $1.4 /Mt · Cache Read $0.26 /Mt $4.4 /Mt”
USD 1.40USD 0.26USD 4.40USD 2.151,048,576not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
17Nscale
Notes and source quote
“| GLM 5.3 | Z.ai | $1.40 | $4.40 |”
USD 1.40not publishedUSD 4.40USD 2.15not statednot statedNscale page
checked 2026-11-15
re-checked 2026-11-16
18Parasail
Notes and source quote
“GLM-5.3 $1.40 $4.40 $0.26”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
19Perplexity
perplexity/glm-5.3
Notes and source quote

Hosted by Perplexity ("Perplexity-Hosted Models"); tool calls billed separately.

“`perplexity/glm-5.3` | 1.40 | 4.40 | 0.26”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedPerplexity page
checked 2026-11-15
re-checked 2026-11-16
20SiliconFlow
Notes and source quote

Context shown as 1049K.

“GLM-5.3 1049K $1.4 $0.26 $4.4”
USD 1.40USD 0.26USD 4.40USD 2.151,048,576not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
21Together AI
Notes and source quote

US geo-pinned option: $1.75 in / $5.50 out.

“GLM-5.3 $1.40 $0.26 (cached) $4.40”
USD 1.40USD 0.26USD 4.40USD 2.15not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
22Venice
z-ai-glm-5-3
Notes and source quote
“| GLM 5.3 | `z-ai-glm-5-3` | $1.75 | $5.50 | $0.325 | — | Private |”
USD 1.75USD 0.325USD 5.50USD 2.6881,000,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
23Amazon Bedrock
Notes and source quote

US cross-region (US CRIS) row; Global CRIS is $1.68 / $5.28 / cache read $0.312. Cache write (30 min) $2.31.

“US CRIS $ 1.848 $ 5.808 $ 0.3432 $ 2.31”
USD 1.848USD 0.3432USD 5.808USD 2.838not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
24SambaNova
GLM-5.3
Notes and source quote
“GLM-5.3 0.14 USD 2.80 USD 8.80 USD”
USD 2.80USD 0.14USD 8.80USD 4.30not statednot statedSambaNova page
checked 2026-11-14
re-checked 2026-11-16
—Mistral AI batch
zai-glm-5-3
Notes and source quote

Third-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Context from the docs model card.

“Z.ai GLM 5.3 ↗ $0.7 $0.07 $2.2 (Batch tab, "Batch (-50%)")”
USD 0.70USD 0.07USD 2.20USD 1.0751,048,576not statedMistral AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot promo
zai-org/GLM-5.3
Notes and source quote

Flex service tier (0.8× standard). Promotional price, 38% off list (list 0.9 in / 4.0 out).

“Flex (0.8×) $0.45 $2.00 $0.10”
USD 0.45USD 0.10USD 2USD 0.83751,048,576FP4DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI flex / spot
accounts/fireworks/models/glm-5p3
Notes and source quote

Fireworks "Spot" mode: 30% off Standard on best-effort capacity; throughput can drop to zero.

“GLM-5.3 Spot $0.182 $0.98 $3.08”
USD 0.98USD 0.182USD 3.08USD 1.5051,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI priority
accounts/fireworks/models/glm-5p3
Notes and source quote

Priority mode.

“GLM 5.3 | Priority $1.75 / $0.325 / $5.50”
USD 1.75USD 0.325USD 5.50USD 2.6881,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—Mistral AI priority
zai-glm-5-3
Notes and source quote

Third-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Context from the docs model card.

“Z.ai GLM 5.3 ↗ $2.45 $0.245 $7.7 (Priority tab, "Priority (+75%)")”
USD 2.45USD 0.245USD 7.70USD 3.7631,048,576not statedMistral AI page
checked 2026-11-15
not auto-checked (page loads prices with JavaScript)
—Baseten fast
Notes and source quote
“GLM-5.3 Fast $2.10 $0.21 $6.60”
USD 2.10USD 0.21USD 6.60USD 3.225not statednot statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI fast
accounts/fireworks/models/glm-5p3
Notes and source quote

Fast mode.

“GLM 5.3 Fast | $2.10 / $0.39 / $6.60 | —”
USD 2.10USD 0.39USD 6.60USD 3.2251,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—BroadNet Inference this site's owner
broadnet/glm-5.3
Same model. Not ranked: BroadRouter is BroadNet's own site. Model page
USD 0.78USD 0.173USD 3.46USD 1.451,048,576not statedpricing.json
synced 2026-11-14

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does GLM 5.3 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on GLM 5.3, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfra (promo)USD 72.00USD 141.00USD 568.13
GMI Cloud (promo)USD 71.82USD 159.96USD 585.90
AkashML (promo)USD 96.30USD 111.60USD 738.00
ChutesUSD 126.63USD 281.19USD 1,052
FriendliAI (promo)USD 129.28USD 287.93USD 1,055
Z.ai (maker)USD 143.64USD 319.92USD 1,172
Alibaba CloudUSD 144.72USD 321.36USD 1,202
BasetenUSD 137.16USD 311.28USD 988.20
Cloudflare Workers AIUSD 143.64USD 319.92USD 1,172
Crusoe CloudUSD 143.64USD 319.92USD 1,172
DigitalOceanUSD 143.64USD 319.92USD 1,172
FeatherlessUSD 143.64USD 319.92USD 1,172
Fireworks AIUSD 143.64USD 319.92USD 1,172
HyperbolicUSD 143.64USD 319.92USD 1,172
Mistral AIUSD 137.16USD 311.28USD 988.20
Novita AIUSD 143.64USD 319.92USD 1,172
NscaleUSD 205.20USD 402.00USD 2,916
ParasailUSD 143.64USD 319.92USD 1,172
PerplexityUSD 143.64USD 319.92USD 1,172
SiliconFlowUSD 143.64USD 319.92USD 1,172
Together AIUSD 143.64USD 319.92USD 1,172
VeniceUSD 179.55USD 399.90USD 1,465
Amazon BedrockUSD 189.60USD 422.29USD 1,547
SambaNovaUSD 266.76USD 612.48USD 1,762
BroadNet Inference (this site's owner)USD 99.70USD 195.40USD 786.69

For the support chatbot, the cheapest price (GMI Cloud, USD 71.82 a month) saves USD 71.82 against the median (USD 143.64). For the coding agent the gap is USD 603.68 a month (52% lower). The winner changes with the workload: DeepInfra wins the cache-heavy agent, GMI Cloud the chatbot.

Which GLM 5.3 provider is cheapest for your traffic?

The cheapest provider depends on how much input you send per output token: below 2.2 input tokens per output token, GMI Cloud; from 2.2 to 5.1, DeepInfra; above 5.1, AkashML. More input, as with long prompts or retrieval, favours a low input price; long answers favour a low output price.

GLM 5.3: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfraUSD 1.047 cheapestUSD 0.8828USD 0.7516
GMI CloudUSD 1.075USD 0.8613 cheapestUSD 0.6903 cheapest
AkashMLUSD 1.243USD 1.243USD 1.243
ChutesUSD 1.881USD 1.514USD 1.22
FriendliAIUSD 1.935USD 1.55USD 1.242
Z.ai (maker)USD 2.15USD 1.723USD 1.381

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 18 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

22 of 24 providers publish a cached-input price below the input price: DeepInfra (78% off), GMI Cloud (81% off), Chutes (80% off), FriendliAI (81% off), Z.ai (81% off) and 17 more. Nscale publishes none, so cached tokens there bill at the input price. AkashML lists a cached price equal to its input price.

Context windows differ: 1,048,576 tokens at DeepInfra, GMI Cloud, AkashML and 7 more; 1,000,000 tokens at Hyperbolic and Venice; 262,144 tokens at Featherless. Z.ai, Alibaba Cloud, Baseten, Cloudflare Workers AI, DigitalOcean and 6 more do not state one. The cheapest row is not always the one that fits a long prompt.

GLM 5.3 on BroadNet Inference

BroadRouter is BroadNet's own site. BroadNet Inference serves this model as broadnet/glm-5.3 at USD 0.78 input, USD 0.173 cached input and USD 3.46 output per 1M tokens, with a 1,048,576-token context. On the 3:1 blend, 3 standard prices above are lower, so pick BroadNet for other reasons: zero data retention and one OpenAI-compatible key for every BroadNet model.

GLM 5.3 on BroadNet: setup, limits and code

What does GLM 5.3 cost in other languages?

The same text needs a different number of tokens in each language. With the GLM 5.3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for GLM 5.3:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.169BroadNet Inference
Arabic MSAUSD 0.322BroadNet Inference
HindiUSD 0.698BroadNet Inference
ChineseUSD 0.463BroadNet Inference
CodeUSD 0.198BroadNet Inference

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Z.ai model card and Epoch AI and may use different settings.

Published benchmark results for GLM 5.3, with sources
BenchmarkResultSetting or noteSource
Terminal Bench 2.188.2Default reasoning_effort max, per the card; Claude Code harnessZ.ai model card, checked 2026-11-16
DeepSWE (v1.1)66.9Default reasoning_effort max, per the card; mini-swe-agent harnessZ.ai model card, checked 2026-11-16
HLE w/ Tools62.5Default reasoning_effort max, per the cardZ.ai model card, checked 2026-11-16
Toolathlon Verified73.0Pass@1 averaged over 3 runsZ.ai model card, checked 2026-11-16
CyberGym84.5Max reasoning effort, Claude Code harnessZ.ai model card, checked 2026-11-16
GPQA Diamond0.909Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
SimpleQA Verified0.41Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
OTIS Mock AIME 2024-20250.911Max reasoning setting; Epoch run glm-5.3_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16

Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Estimate your own bill

The Z.ai models whose cheapest standard price is closest to GLM 5.3's (USD 1.047 blended):

Z.ai models priced closest to GLM 5.3
ModelCheapest inputCheapest outputMax contextProviders
GLM-4.5-FP8USD 0.60USD 2.20131,0722
GLM 5USD 0.60USD 1.92204,80010
GLM 4.5VUSD 0.60USD 1.8065,5362
GLM 5.2USD 0.5625USD 1.801,048,57619
GLM 5.1USD 0.90USD 2.90204,80012
GLM 4.6USD 0.43USD 1.75204,8006

Priced closest from other makers: Kimi K2 Instruct 0905 (Moonshot AI, USD 1.075) · Qwen3.5 397B A17B (Qwen, USD 1.087) · Kimi K2 Instruct (Moonshot AI, USD 1.002).

Compare GLM 5.3 with

Also compared: vs GLM 5.2 · vs DeepSeek V4 Pro · vs MiniMax M3 · vs Qwen3.8 27B · vs Kimi K3 · vs Claude Sonnet 5.5 · vs DeepSeek V4.1 Flash · vs NVIDIA Nemotron 3 Ultra · vs Kimi K2.5 · vs DeepSeek V4 Pro 0813 · vs Kimi K2.6 · vs GLM 5.3 FlashX · vs Kimi K2 Instruct 0905 · vs Kimi K2 Instruct · vs Qwen3.6 Plus · vs DeepSeek R1 · vs Kimi K2.7 Code.

Every GLM 5.3 price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the GLM 5.3 API cost per token?

From USD 0.19 per 1M input tokens (USD 0.00000019 per token) and USD 2.20 per 1M output tokens (USD 0.0000022 per token) at the lowest standard prices we found, which can come from different providers. The median of 24 standard prices is USD 1.40 input and USD 4.40 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for GLM 5.3?

Among the 24 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 1.047 per 1M). For input alone the lowest price is USD 0.19 (AkashML); for output alone, USD 2.20 (GMI Cloud). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is GLM 5.3 cheaper from a host than from Z.ai?

Yes. DeepInfra charges USD 0.5625 input and USD 2.50 output per 1M tokens, 51% below Z.ai's own USD 1.40 / USD 4.40 on the 3:1 blend (a promotional price).

Does GLM 5.3 have cached input pricing?

23 of 24 standard prices include one. The lowest is USD 0.125 per 1M at DeepInfra; the median is USD 0.26. Providers without one bill cached input at the input price. What cached input means.

What is the GLM 5.3 context window?

Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (Featherless, Hyperbolic and Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on GLM 5.3?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 568.13 a month at DeepInfra, USD 1,172 at the median price and USD 2,916 at Nscale. Try your own numbers.

Is there a batch, flex or priority price for GLM 5.3?

Yes: batch from Mistral AI at USD 0.70 / USD 2.20; flex / spot from DeepInfra at USD 0.45 / USD 2; priority from Fireworks AI at USD 1.75 / USD 5.50; fast from Baseten at USD 2.10 / USD 6.60 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is GLM 5.3 free to use through an API?

No provider in our data lists a free price for GLM 5.3 as of 2026-11-15. BroadNet Inference serves it as broadnet/glm-5.3 to paid accounts only: the USD 5 starting credit does not cover it (rate card synced 2026-11-14). Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Can I use GLM 5.3 on BroadNet Inference?

Yes. BroadNet Inference serves GLM 5.3 as broadnet/glm-5.3 at USD 0.78 input, USD 0.173 cached and USD 3.46 output per 1M tokens (rate card synced 2026-11-14), with zero data retention. On the 3:1 blend, 3 standard prices on this page are lower. BroadRouter is BroadNet's own site. GLM 5.3 on BroadNet.

How does GLM 5.3 score on benchmarks?

As published, the Z.ai model card reports 88.2 on Terminal Bench 2.1 and 66.9 on DeepSWE (v1.1); Epoch AI measured 0.909 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity