All 22 DeepSeek V4.1 Flash endpoints match reference — 3.9-point range, most consistent model in the Index
ArtificialAnlys · x · 2026-11-06
Supplementary data from Artificial Analysis' Endpoint Accuracy Index: all 22 DeepSeek V4.1 Flash 1017 endpoints are statistically in line with the reference, scoring 97.5–101.4 — a 3.9-point range that makes it the most consistent model in the Index. By contrast, GLM-5.3 spans 26 endpoints scoring 67.2–99.3 with 10 below reference; the largest gaps stem from output token caps and reasoning loops truncating HLE-250 answers, not quantization (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