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
| Benchmark | GLM-5.3-Flash | AZ-Focus | 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 |
| SWE-bench Verified, first 100 (mini-SWE-agent, two runs) | 95 / 95 | 93 / 91 | |
| τ²-bench airline / retail (two runs)† | 0.89 / 0.919 | 0.88 / 0.905 |
Thinking on, Z.AI's recommended sampling, same serving setup for both models. Single runs on a few hundred questions move by about a point either way. 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.
Same architecture, tokenizer and chat template as GLM-5.3-Flash (the template is Z.AI's, revision a6c167b, which keeps
image and video input working in engines that check for it). The routed experts are EXL3 4 bpw with the mcg
codebook; load it with an engine that supports GLM-5.3-Flash's EXL3 layout. 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). azfocus_provenance.json lists the source of every
file.
Questions, or want to build on this with us? hello@axonzeta.ai