MiniMax's 430B model beats 3T-scale rivals on AA knowledge benchmark
teortaxesTex · x · 2026-10-24
Sharing Artificial Analysis's AA-Omniscience knowledge chart, teortaxesTex argues "MiniMax won — better knowledge in 430B than in a 3T model, best AI startup in China." The leaderboard is topped by Claude Falback 5.1 variants (66-67%) and GPT-6/6.1 (62-65%); MiniMax's model hits 51%, ahead of Gemini, Grok, GPT-6 Luna, DeepSeek and Muse, with Qwen3.8 27B at the bottom (16%).
More from Models
- Kimi K3.1 Pro vs GPT-6 Astra vs Opus 5.5: Building Star Trek's Enterprise D in Minecraft — Angaisb_ · 2026-10-24
- Kimi 3.1 Pro priced like Argon but scores like DeepSeek V4.1 Flash on meme 'Runescape Bench' — scaling01 · 2026-10-24
- Jon Barron details his workflow: Gemini runs experiments, drafts the paper, then rewrites in his style — jon_barron · 2026-10-24
- Users praise Gem Argon for cultural fluency: a frontier model that roots for you — sebkrier · 2026-10-24
- User says Opus silently downgraded to 4.8 mid-task, then told him to talk to people — natesiggard · 2026-10-24
- Suspicious new GitHub accounts reference Qwen4 in Alibaba T-Head repo PRs — brainExploded99 · 2026-10-24