GLM-5.3-Flash
glm-flash
Native multimodal GLM model for efficient coding and long-horizon agent tasks
ReasoningTool CallingAttachmentsOpen Weights
Context Window
1M
Max Output
131K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
N/A
Released
2026-08-26
Last Updated
2026-08-26
Modalities
Input:TextImageVideoPDF
→Output:Text
Benchmarks
| Benchmark | Score | Metric | Harness |
|---|---|---|---|
| Terminal-Bench | 84.3 | pass@1 | Claude Code 2.1.207 |
| DeepSWE | 63.4 | resolved | mini-swe-agent |
| Agents' Last Exam | 26.3 | score | - |
| AutomationBench | 48.8 | pass@1 | - |
| Humanity's Last Exam | 55.3 | accuracy | - |
| GDPval-AA | 1773 | Elo | - |
Available Providers (0)
Tidak ada provider yang terdaftar untuk model ini.