DeepSeek scores ~5 pts higher on Artificial Analysis index than Epoch ECI
scaling01 · x · 2026-10-29
A shared comparison chart shows DeepSeek's 10 models correlate strongly (r=0.973) between Artificial Analysis' AA Progress Index and Epoch's ECI, but AA rates DeepSeek systematically higher — a mean offset of 5 points above the all-model fit line, widening to 13 points since July 2025. Models like DeepSeek V4 Pro 0813 and V4.1 Flash sit above the line, prompting the quip "DeepSeek is AA maxxing."
More from Models
- Nat Lambert Mocks Teased 'Gemini 4 Carbon' as a Graspy Preemptive Move — natolambert · 2026-10-29
- Unverified 'Gemini 4 Carbon' SOTA claims circulate alongside Google Docs ranking jab — gnukeith · 2026-10-29
- DeepMind's Samuel Albanie: new model's hallucination rate much improved over Argon — SamuelAlbanie · 2026-10-29
- User pushback: US AI models are 'heavily censored' and less useful — gnukeith · 2026-10-29
- Gemini 4 Carbon tops AA Index at 59, but loses FrontierSWE to GPT-6 Astra — faraz0x · 2026-10-29
- Google slammed for slow releases: rivals may outperform Gemini 4 Carbon before it ships — Angaisb_ · 2026-10-29