GLM-5.3-Flash hits #1 on Artificial Analysis with 294 tok/s
Arindam_1729 · x · 2026-09-01
Zai's open-source model GLM-5.3-Flash (aka Ox Alpha) has claimed the top spot on the Artificial Analysis leaderboard. Running on Nebius, the model achieves a record-breaking inference speed of 294 tokens per second.
Key features:
- Blazing Speed: 294 output tokens/s, ideal for latency-sensitive apps.
- Massive Context: 1M token context window.
- Privacy First: Zero data retention policy.
- Multimodal: Capable of processing multiple modalities.
Related event: GLM-5.3-Flash Tops Inference Speed Charts on Nebius(2 posts)→
More from Infra
- Zephon brings elastically deterministic data loading to TorchTitan with identical batches across GPU counts — josh_wills · 2026-10-17
- vLLM serves Reflection Beam 501B MoE from day 0, hitting 708 tok/s with DFlash2 — woosuk_k · 2026-10-17
- Zephon x TorchTitan: bit-identical global batches when resuming training on different GPU counts — PyTorch · 2026-10-17
- Jensen Huang: AI shifting from retrieval to problem-solving may need a billion times more compute — rohanpaul_ai · 2026-10-17
- Haight Street Compute Market: a one-day trading floor for compute deals in SF — Scobleizer · 2026-10-17
- eigenrobot welcomes a possible local data center, citing rising property taxes — eigenrobot · 2026-10-17