Artificial Analysis Endpoint Accuracy Index Shows Quarter of Endpoints Below Baseline

Artificial Analysis released Endpoint Accuracy Index v1.1, finding nearly a quarter of inference endpoints below reference baselines. DeepSeek V4.1 Flash was the most consistent across all 22 endpoints, while GLM-5.3 spanned 26 endpoints with scores ranging widely from 67.2 to 99.3.

2026-11-06 ~ 2026-11-06 · 4 related posts

• Artificial Analysis launches Endpoint Accuracy Index v1.1: nearly 1 in 4 serverless endpoints score below reference — ArtificialAnlys · 2026-11-06
• GLM-5.3 has the most endpoints in the Accuracy Index but widest spread: 67.2 to 99.3 across 26 endpoints — ArtificialAnlys · 2026-11-06
• All 22 DeepSeek V4.1 Flash endpoints statistically in line, most consistent model in the Index — ArtificialAnlys · 2026-11-06
• All 22 DeepSeek V4.1 Flash endpoints match reference — 3.9-point range, most consistent model in the Index — ArtificialAnlys · 2026-11-06