GLM-5.3 endpoint posts 92.8% error rate as Artificial Analysis starts counting failed requests
ArtificialAnlys · x · 2026-11-05
Artificial Analysis updated its API performance benchmark: failed requests — errors, rate limits and timeouts — now score a speed of 0, and each endpoint gets an Endpoint Error Rate metric.
For GLM-5.3, the endpoints with the fastest streaming take 18–26 seconds to return the first token (vs 1–3 seconds for most others), so they fall down the speed rankings once that wait counts toward total request time. The chart shows one ULTRA GLM-5.3 (Max) endpoint averaging a 92.8% error rate, while most other providers sit at 0%.
Related event: GLM-5.3 Suffers High Latency and Error Rates in New Benchmark Rankings(2 posts)→
More from Infra
- LFM3-Omni-2B ported to run fully offline on iPhone at ~80 tok/s with custom WebGPU kernels — JosephJacks_ · 2026-11-05
- Orbital Data Centers Launch to Sun-Synchronous Orbit, Memed as Elves Sailing West — rand_longevity · 2026-11-05
- Vietnam's Lâm Đồng to bring Starlink to mountain areas where poor signal hampers rescue — elonmusk · 2026-11-05
- SpaceX partners with Qualcomm for nationwide Starlink Mobile 5G network from 2027 — Polymarket · 2026-11-05
- Stopping runaway agent spend before the bill: pre-call guardrails and three gaps found the hard way — MaverikSh · 2026-11-05
- US AI scale faces two physical gates: delivered power and manufacturing — ingliguori · 2026-11-05