LithosAI sweeps 12 #1 spots on Artificial Analysis, GLM 5.3 Flash at 1,543 tok/s
JiaZhihao · x · 2026-10-21
Inference provider LithosAI claims 12 first-place rankings on Artificial Analysis across four open models — GLM 5.3 Flash, Kimi K3, DeepSeek V4.1-Flash, and GLM 5.3 — leading in output speed, time to first token, and end-to-end response time, with GLM 5.3 Flash reaching up to 1,543 tok/s without sacrificing quality. It has led since its public API launch in September, targeting latency-sensitive agentic workloads like coding, SRE, cybersecurity, and voice AI.
More from Infra
- Corporate token spending growth collapses from 42% to 0.2% as hyperscaler ROIC falls to 20% — SumitGup · 2026-10-21
- Qualcomm plans worldwide performance-based layoffs as it chases $5B AI data center revenue — rohanpaul_ai · 2026-10-21
- vLLM at PyTorchCon 2026: KV cache and kernel optimizations across TPU, AMD, and NVIDIA — PyTorch · 2026-10-21
- antirez to port DeepSeek Infer kernels to DGX Spark's SM121 for DwarfStar — antirez · 2026-10-21
- Ternary-Bonsai-2-9B: 2-bit ternary vision-language model trends on Hugging Face for on-device use — prism-ml · 2026-10-21
- General Compute x Positron: GPUs Handle Prefill, Memory-First Chips Tackle Decode-Bound LLM Inference — cneuralnetwork · 2026-10-21