LLMs predict MtG set win rates pre-release; Claude Opus 5.5 does best
Jsevillamol · x · 2026-10-22
A user asked LLMs to predict win rates of the newest Magic: The Gathering set before release and compared them with community tier lists. Outcomes varied widely across models, with Claude Opus 5.5 doing the best among them. Full details are published on a companion page.
More from Models
- BitKindle: AI bootstraps a full C compiler from a 3,584-byte machine-code seed — dotey · 2026-10-22
- A tokenization-shared open model ladder is sorely missing, and all roads lead to Qwen — bclavie · 2026-10-22
- Chonk DOOM: a DOOM-like shooter built for Mistral Large 4 to beat on its own — GuillaumeLample · 2026-10-22
- DeepSeek V4.1 Pro rumored to train on 50T+ pretraining tokens, matching Microsoft's scale — teortaxesTex · 2026-10-22
- Research finds multimodal models rarely actually look at images — MoonL88537 · 2026-10-22
- OpenAI Voice Mode Users Hit Long Wait Queues Even on Pro Plan — deviltalk · 2026-10-22