GDPx and Epoch's ECI leaderboards nearly agree, Spearman ρ=0.983 across 17 models
scaling01 · x · 2026-11-03
Account scaling01 highlights that GDPx, despite using a completely different methodology and task set from Epoch AI's ECI leaderboard, produces nearly identical model rankings: across 17 models scored by both, Spearman ρ=0.983 and Kendall τ=0.912, with disagreements only where ECI has fewer than 15 benchmarks.
Per the accompanying chart: GPT-6 Astra (11.8%) and Claude Opus 5.5 lead both lists, Gemini 4 Argon ranks 7th; DeepSeek V4.1 Flash, Qwen 3.8 Max, Kimi K3 and GLM-5.3 cluster in the 10-14 range, showing a persistent gap between top US and Chinese labs.
More from Models
- Sebastian Raschka Maps October's 'Open October': 10 Open LLM Architectures in One Month — rasbt · 2026-11-03
- Kimi K3.1 accused of recalling hidden Terminal-Bench test rules it was never given — maksym_andr · 2026-11-03
- First hands-on: Meta's Muse Wonder 1.0 vs DeepSeek V4.1 Flash in Codex CLI — Richidm · 2026-11-03
- "Claude Code has been terrible today" — developer smells a new Opus launch coming — hermanschutte · 2026-11-03
- Mistral releases open-weight ML4 with frontier code-agent and cyber capabilities — _AndrewZhao · 2026-11-03
- Stealth-routed Fable 5.5 vs GPT 6.2 Astra compared on drawing a PS5 controller — WaqarKhanHD · 2026-11-03