Effort: max
zai-orgReleased Aug 26, 2026
GLM-5.3-Flash
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 reducing compute overhead.
Context window1M
Max output943.7K
Provider endpoints46
Benchmark results19
Agent runs1
Measured performance
All leaderboards ↗Benchmark results
Effort: max
GDPval-AA ↗2.1
1,642.18Effort: max
AutomationBench-AA ↗AA Index 4.3.2 collection
60.37%Effort: max
Effort: max · Harness unreported
SciCode ↗AA Index 4.3.2 collection
51.62%AA · Under reviewEffort: max
Humanity’s Last Exam ↗AA Index 4.3.2 collection
39.85%Effort: max
GDP.pdf ↗AA Index 4.3.2 collection
15.4%Effort: max
CritPt ↗AA Index 4.3.2 collection
15.43%AA · Under reviewEffort: max
AA-Omniscience ↗AA Index 4.3.2 collection
7.47Effort: max
AA-LCR ↗1.1
80%Effort: max
LiveBench Overall ↗2.0 · 2026-10-14 (dataset 2026-09-02)
70.61%Effort: max · single run · equal mean of 7 suites
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)
77.2%Effort: max · single run
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)
70.1%Effort: max · single run
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)
84%Effort: max · single run
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)
80.6%Effort: max · single run
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)
28.4%Effort: max · single run
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)
76.4%Effort: max · single run
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)
77.6%Effort: max · single run
Provider measurements
1 configurationSpeed
≈10K input tokens1 requestmedian / 72h
Artificial Analysis · first-party providers · serving endpoint not reported
Z AI
GLM-5.3-Flash
Reasoning max
- Output rate
- 70.8312 tok/s
- Time to first chunk
- 2.77334 s
Last checked Source ↗
Methodology 2.2.0 & measurement details
First chunk includes request processing and network time, and may include reasoning.
- Prompt
- long · ≈10,000 input tokens
- Parallel requests
- 1
- Minimum answer
- 1,500 tokens
- Aggregation
- median over 72 hours
- Token counting
- o200k_base
- Benchmark client
- Google Cloud us-central1-a
- Serving endpoint
- Not reported
- Serving region
- Not reported
- Sample size
- Not reported
- Window end
- Not reported
Model + harness
All agent results ↗Agent runs
Terminal-Bench 4.0
claude-code2.1.285
Reasoning effort none
Tested model identity
GLM-5.3-Flashz-ai/glm-5.3-flashPass rate35.76%
95% CI 32.22%–39.3%
n = 330Checked
Access & cost
47 quotesPrices across providers
Your token mix
USD · listed token ratesOpenRouter
Catalog quote- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
novita
via Hugging Face- Input
- $0.15
- Output
- $0.50
together
via Hugging Face- Input
- $0.15
- Output
- $0.50
fireworks-ai
via Hugging Face- Input
- —
- Output
- —
featherless-ai
via Hugging Face- Input
- —
- Output
- —
zai-org
via Hugging Face- Input
- —
- Output
- —
baseten
via Hugging Face- Input
- $0.15
- Output
- $0.50
deepinfra
via Hugging Face- Input
- $0.15
- Output
- $0.50
- Input
- $0.15
- Output
- $0.50
Experiential
Standard list rate
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
Catalog list rate. Plan allowances and temporary discounts are separate.
Together AI
Serverless · quantization=FP4
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
Organization: Z.ai
Fireworks AI
Standard · service_tier=default
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
Fireworks AI
Standard · service_tier=priority
- Input
- $0.1875
- Output
- $0.625
- Cached input
- $0.0375
- Input
- $0.06
- Output
- $1.60
- Cached input
- $0.04
- Input
- $0.075
- Output
- $0.25
- Cached input
- $0.015
Source discount 50%; rates as published
- Input
- $0.075
- Output
- $0.25
- Cached input
- $0.015
Source discount 50%; rates as published
- Input
- $0.075
- Output
- $0.50
- Cached input
- $0.0075
- Input
- $0.075
- Output
- $0.50
- Cached input
- $0.0075
- Input
- $0.0784
- Output
- $0.30
- Cached input
- $0.0522
- Input
- $0.0784
- Output
- $0.30
- Cached input
- $0.0522
- Input
- $0.08
- Output
- $0.50
- Cached input
- $0.012
- Input
- $0.0825
- Output
- $0.275
- Cached input
- $0.0165
Source discount 45%; rates as published
- Input
- $0.084
- Output
- $0.28
- Cached input
- $0.0168
Source discount 44%; rates as published
- Input
- $0.084
- Output
- $0.65
- Cached input
- $0.03
- Input
- $0.09
- Output
- $0.30
- Cached input
- $0.018
Source discount 40%; rates as published
- Input
- $0.10
- Output
- $0.8625
- Cached input
- $0.075
- Input
- $0.12
- Output
- $0.388
- Cached input
- $0.032
- Input
- $0.12
- Output
- $0.50
- Cached input
- $0.06
- Input
- $0.1275
- Output
- $0.425
- Cached input
- $0.0255
Source discount 15%; rates as published
- Input
- $0.1313
- Output
- $0.4375
- Cached input
- $0.03
- Input
- $0.14
- Output
- $0.47
- Cached input
- $0.024
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.02
Endpoint degraded (status -5)
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.03
- Input
- $0.1875
- Output
- $0.625
- Cached input
- $0.0375
- Input
- $0.225
- Output
- $0.75
- Cached input
- $0.045
- Input
- $0.25
- Output
- $0.70
- Cached input
- $0.075
Offers for this model
1 offerExperiential Labs · Discount
2.5% off · Experiential Pro model discounts
Paid Pro plan required, covering the first 2,000 credits of usage each month, then list price.
Checked Source ↗
Model specifications
- Developer
- zai-org
- Modality
- Language
- Context
- 1,048,576 tokens
- Maximum output
- 943,717 tokens
- Weights
- Open weights
- Released
- Aug 26, 2026
- Provider listed
- Aug 25, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
z-ai/glm-5.3-flash - huggingface
zai-org/GLM-5.3-Flash - deepinfra
zai-org/GLM-5.3-Flash - experiential
glm-5.3-flash - artificial-analysis
19496b81-9f41-4214-a77a-1df803b3c5ae - livebench
glm-5.3-flash
Sources
Updated Oct 17, 2026
More from zai-org
View all ↗No reported score
Price not listed
No reported score
Price not listed
zai-orgReleased Aug 18
GLM-5.3
Reuses the GLM-5.2 base with new post-training; exposes low, high and max reasoning effort, defaulting to max.
1M contextTool callingStructured output
zai-orgListed Jun 16
GLM-5.2
GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on…
1M contextTool callingStructured outputNo reported score
No reported score