โฝ๏ธIntroducing ๐๐๐ ๐๐จ๐๐๐๐ซ๐๐ซ๐๐ง๐: a benchmarking platform for real-world LLM predictions
โ
Predictions for 104 games @FIFAWorldCup with frontier LLMs
๐Opus 4.8: Spain / GPT-5.5: Spain / Grok 4.3: Argentina / Mistral-large: France
โก๏ธAll predictions & leaderboard llmsoccerarena.up.railway.app
llmsoccerarena.up.railway.app
Compare football score predictions from multiple LLMs.
Stefan Feuerriegel