GLM-5.3-Flash
Z.ai- Arena score
- 1472
- Among open models
- #3of 148
- Among all on Arena
- #30
- Votes
- 51,019
Measured on GLM-5.3-Flash, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
Top 10 among open models in#1Coding#1Math#1Software & IT#2Chinese
CategoryScoreOpen rankArena rankVotes
- Chinese1528#2#253.9K
- Expert1511#3#205K
- Coding1509#1#1612.9K
- Math1503#1#152.5K
- Software & IT1501#1#1819K
- Hard prompts, English1492#4#2311.9K
- Applied math1491#4#282.9K
- Hard prompts1490#3#2232.6K
- French1489#2#261.9K
- Science1485#4#298.2K
- Long prompts1481#3#2822.3K
- Instructions1480#3#2217.6K
- Medicine & health1480#4#303.4K
- Legal & government1478#5#374K
- Excluding ties1477#3#3137.8K
- English1477#4#3118.3K
- Spanish1476#4#231.9K
- Multi-turn1471#5#387.8K
- Russian1467#4#377.6K
- Non-English1462#3#3332.7K
- Business & finance1461#6#369.1K
- Writing & literature1457#5#3714.3K
- Japanese1453#3#33943
- German1452#11#56865
- Polish1448#10#56897
- Creative writing1442#6#4411K
- Media & sports1442#7#3913K
- Korean1427#5#39832
Discussion
- Build & Train a GLM-5.3-Flash Model From Scratch with PythonfreeCodeCamp.org · Oct 6, 20262.7K likes
- GLM-5.3-FlashPhilpax · Aug 26, 20261.1K points
- Cancel your subscriptions, Ox-Alpha is here! (GLM 5.3 Flash)Matthew Berman · Aug 29, 20262.5K likes
- One month coding with GLM 5.3 FlashThibWeb · Oct 2, 2026234 points
- I Tested Deepseek V4.1 Flash vs Qwen 3.8 Flash, GLM 5.3 Flash, Gemini 3.8 FlashRemakeBench · Sep 18, 20261.4K likes
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiopeasantsmith/GLM-5.3-Flash-Maya-GGUF86 builds
- MLX · Apple silicon: mlx-lm, LM StudioJundot/GLM-5.3-Flash-oQ4e-mtp45 builds
- AWQ · vLLM, SGLangspele1100/GLM-5.3-Flash-AWQ-INT41 build
- GPTQ · vLLM, SGLangcanada-quant/GLM-5.3-Flash-W4A16-MTP2 builds
Most downloaded
- GLM-5.3-Flash-Maya-GGUFpeasantsmith · Quantization1.4M downloads
- GLM-5.3-Flash-GGUFunsloth · Quantization743.3K downloads
- GLM-5.3-Flash-NVFP4tattrongvu · Quantization87K downloads
- GLM-5.3-Flash-NVFP4nvidia · Quantization52.5K downloads
- GLM-5.3-Flash-Uncensored-RCO-GSQ-GGUFGCSA-AiLab · Quantization50.8K downloads
BenchClub runs
Not runnable yet
Runs open once a GLM-5.3-Flash build is registered.
More from Z.ai
See more
GLM-5.31.7M753B
GLM-51.2M754B
GLM-4.7-Flash1.2M31.2B
GLM-5.1746.3K754B
Other >300B models
See more
DeepSeek-V3.2DeepSeek9.6M685B
InklingThinking Machines1.5M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B

Kimi-K3Moonshot AI768.9K2.8T