GLM-5.3
Latest GLM-5.3Flagship GLM model for long-horizon coding, agents, and complex project delivery
- Strongest at
- Writing Top 12% of the past year's models · 4 of 4 benchmarks
- Price per 1M tokens
- $1.4 / $4.4 input / output · Zai
- Context window
- 1M tokens in · 131.1K out
- Since the last one
- 62 days after GLM-5.2
Capability profile
Scored against 91 models released in the past year. 50 is the average model; further out is better.
No results yet: Visual reasoning
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow dot rests on a single benchmark.
- Coding DeepSWE, FrontierCode, LiveBench: Coding + Agentic Coding
- Writing EQ-Bench Creative Writing v3, EQ-Bench Longform Writing, Lech Mazur Writing comparison, LiveBench: Instruction Following
- Reading & documents LiveBench: Language + Data Analysis
- Reasoning Chess Puzzles, Mystery Game Puzzles, LiveBench: Reasoning
- Math OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private, ProofBench, LiveBench: Mathematics
- Science GPQA diamond, Terminal-Bench Science 0.1, WeirdML v2
- Computer use Terminal-Bench 4.0, APEX-Agents
Price against capability
The shaded corner holds anything better and cheaper. Prices blend input and output 3 to 1.
2 models from the past year score higher on Writing for less: Muse Spark 1.3, Gemini 3.8 Flash.
3 models from the past year score higher on Coding for less: DeepSeek V4.1 Flash, Muse Spark 1.3, DeepSeek V3.2.
16 models from the past year score higher on Reading & documents for less: Gemini 3 Flash Preview, GPT-6.1 Terra, Qwen3.5 9B and 13 more.
12 models from the past year score higher on Reasoning for less: GPT-6.1 Terra, Gemini 3.8 Flash, DeepSeek V4.1 Flash 1017 and 9 more.
16 models from the past year score higher on Math for less: GPT-6.1 Terra, Claude Haiku 5.5, Muse Spark 1.3 and 13 more.
25 models from the past year score higher on Science for less: Gemini 3.8 Flash, GPT-6.1 Terra, DeepSeek V4.1 Flash 1017 and 22 more.
4 models from the past year score higher on Computer use for less: Claude Haiku 5.5, Qwen3.8 27B, DeepSeek V4 Pro 0813 and 1 more.
OpenRouter $0.07 / $1.4 · Zai $1.4 / $4.4 · Cached input $0.26
Since GLM-5.2
9 releases in the GLM-5.3 line.
Epoch benchmark boards
Best result on each board it has run. The tick marks the leader.
5 more boards
Z.ai's past year
12 release days in the past year, about one every 30 days. The next is expected around Nov 21, 2026. Forecasts ↗
Specifications
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.