GLM-5.3 benchmarks, pricing and specs
GLM-5.3 is a Z.ai model released on August 18, 2026 that takes text input and produces text. It costs $1.40 per 1M input tokens and $4.40 per 1M output tokens and accepts up to 1,000,000 tokens of context. It scores 1478 Elo on Arena Text, #18 of 49 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $1.40
- Per 1M output tokens
- $4.40
- Context window
- 1M
- Arena Text
- 1478 Elo · #18/49
Data verified October 13, 2026 · Dataset 2026-10-13
Key facts
- Provider
- Z.ai
- Model family
- GLM-5
- Release date
- August 18, 2026
- Status
- Current
- Access
- API and open weights
- API model id
- glm-5.3
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- text
- Output
- text
- Task families
- text
- Declared capabilities
- reasoning, coding, agentic coding
GLM-5.3 pricing
It is the #23 cheapest of 47 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Z.ai's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1478 Elo | #18 of 49 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 90.9% | #22 of 40 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 68.8% | #21 of 40 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 41% | #27 of 36 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Zhipu reports a 50% gain over GLM-5.2 on its Z.ai Code Bench, from post-training on the same base model
- Open weights under the GLM-5.3 License, and an API that accepts OpenAI Chat Completions, OpenAI Responses and Anthropic Messages requests
- A 1M-token context window with up to 128K output tokens
Cautions
- Text input only, and reasoning cannot be turned off: requests that disable thinking fail
- The licence requires a Z.ai security review before very large model-as-a-service operators use it commercially
Best for
- Long-horizon agentic coding
- Self-hosted reasoning with permissive weights
Alternatives to GLM-5.3
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
MiMo-V2.6-Pro
- 69% cheaper per 1M input tokens, $0.435 vs $1.40
- 2 points higher on Arena Text, 1480 vs 1478
- From Xiaomi MiMo
Mistral Large 4
- 3% cheaper per 1M input tokens, $1.36 vs $1.40
- 49 points lower on Arena Text, 1429 vs 1478
- From Mistral AI
DeepSeek-V4-Pro
- 6% cheaper per 1M input tokens, $1.32 vs $1.40
- 13 points lower on Arena Text, 1465 vs 1478
- From DeepSeek
Gemini 3.6 Flash
- 7% more per 1M input tokens, $1.50 vs $1.40
- 4 points higher on Arena Text, 1482 vs 1478
- From Google
Compare GLM-5.3 with
Other GLM-5 models
GLM-5.3 FAQ
How much does GLM-5.3 cost?
GLM-5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens at the standard tier. It is the #23 cheapest of 47 current text models priced per 1M input tokens. Source: Z.ai, verified October 13, 2026.
What is the context window of GLM-5.3?
GLM-5.3 accepts up to 1,000,000 tokens of context. It can return up to 128,000 tokens in one response. That ranks #25 of 57 current text models by context length.
How does GLM-5.3 score on independent benchmarks?
GLM-5.3 scores 1478 Elo on Arena Text, #18 of 49 current models (Arena, measured October 8, 2026), 90.9% on GPQA Diamond, #22 of 40 current models (Epoch AI, measured October 12, 2026) and 68.8% on FrontierMath Tiers 1-3 (v2), #21 of 40 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not Z.ai's own launch figures.
Is GLM-5.3 open source or API only?
GLM-5.3 is available both through Z.ai's API and as open weights you can run yourself.
What are the best alternatives to GLM-5.3?
The closest current alternatives by price and measured performance are MiMo-V2.6-Pro (69% cheaper per 1M input tokens, $0.435 vs $1.40), Mistral Large 4 (3% cheaper per 1M input tokens, $1.36 vs $1.40), DeepSeek-V4-Pro (6% cheaper per 1M input tokens, $1.32 vs $1.40) and Gemini 3.6 Flash (7% more per 1M input tokens, $1.50 vs $1.40).
Sources
- GLM-5.3 documentation · Z.ai · official · verified October 13, 2026
- Z.ai release notes · Z.ai · official · verified October 13, 2026
- Z.ai API pricing · Z.ai · official · verified October 13, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "GLM-5.3 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/glm-5-3
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether GLM-5.3 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls