GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AxonZeta
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AxonZeta
Model Tree
zai-org/GLM-5.3-Flash
Input Modalities
Output Modalities
Supported Functionality
This FP8 build, against Z.AI's FP8 release, both served with vLLM on the same hardware:
| Benchmark | GLM-5.3-Flash FP8 | AZ-Focus FP8 | Thinking tokens |
|---|---|---|---|
| Reasoning and knowledge (48 questions: 24 MMLU-Pro, 24 BIG-Bench Hard) | 35/48 · 2,351 tokens | 35/48 · 1,169 tokens | 50% less |
| SWE-bench Verified, first 100 (mini-SWE-agent) | 96 | 94 / 93 (two runs) |
The same edit on the 4-bit EXL3 build (a slightly stronger setting), for a wider picture:
| Benchmark | GLM-5.3-Flash | AZ-Focus EXL3 | Thinking tokens |
|---|---|---|---|
| MMLU-Pro (500 questions) | 86.2% · 2,114 tokens | 86.8% · 1,289 tokens | 39% less |
| BIG-Bench Hard (540 tasks) | 83.7% · 634 | 84.1% · 326 | 49% less |
| AIME 2025 (30, 2 runs)† | 75.0% · 16.5k | 81.7% · 11.2k | 32% less |
| GPQA Diamond (198)† | 80.8% | 82.3% | ~20% less |
| HumanEval+ & MBPP+ (EvalPlus)† | 85.8% | 86.9% | ~40% less |
| τ²-bench airline / retail (two runs)† |
Thinking on, Z.AI's recommended sampling, same serving setup for both models in each table. Single runs move by about a point either way (a few tasks on SWE-bench). SWE-bench runs used a 12-hour limit per task sandbox. None of these benchmarks was used to build the model. † Measured on an earlier build of the same edit.
AZ-Focus works best at max or high effort, where most of the hesitation is. At low effort GLM-5.3-Flash already thinks very little, and the edit costs accuracy without saving much (BBH 80.0% vs 83.5%, MMLU-Pro 83.0% vs 84.2%). Use the original if you run at low effort.
Use it exactly like Z.AI's GLM-5.3-Flash FP8 release: same architecture, tokenizer, chat template, file layout and size, served with the same engines and settings. No adapter, patch or extra code. The difference shows in thinking mode; with thinking off, output length is unchanged.
MIT, as for the original model. Based on GLM-5.3-Flash by Z.AI
(Copyright (c) 2026 Z.AI Co., Ltd; see LICENSE and NOTICE).
Questions, or want to build on this with us? hello@axonzeta.ai
| 0.89 / 0.919 |
| 0.88 / 0.905 |