GLM-5.3 has the most endpoints in the Accuracy Index but widest spread: 67.2 to 99.3 across 26 endpoints
ArtificialAnlys · x · 2026-11-06
Supplementary data from Artificial Analysis' Endpoint Accuracy Index v1.1: GLM-5.3 has the most endpoints covered at 26, scoring 67.2–99.3, with 16 statistically in line and 10 below reference. The three largest gaps come from output token caps and reasoning loops cutting off HLE-250 answers; quantization is not a cause — five of six FP4 endpoints match the FP8 reference.
More from Infra
- Vivek Wadhwa: Big Tech's trillion-dollar bet on data centers is a mistake — sanjaykalra · 2026-11-06
- Is AMD 7900 XT/XTX viable for video generation in late 2026? — Beneficial_Fish_7509 · 2026-11-06
- Blue Origin unveils Northstar engine: 715,000 lbf thrust, 30% lighter than BE-4 — beffjezos · 2026-11-06
- DFlash drafts whole token blocks in parallel to fix speculative decoding bottleneck — Lianhuiq · 2026-11-06
- A single desktop B70 runs an entire AI livestream radio, generating music in real time — prince_pringle · 2026-11-06
- Inferact, founded by vLLM creators, now serves 7 trillion tokens a day — Xianbao_QIAN · 2026-11-06