Arena Overview section is heavily biased towards languages. grok-4.1-thinking is worse than claude-opus-4-5-20251101-thinking-32k on every non-language metric by a large margin but somehow ranks higher overall, maybe because opus is way worse Spanish and Korean?
Cookie Banner conflicts with cloudflare anti bot stuff
Site is unusable.
While GPT-5.2 scores well on benchmarks, human preference is important for OpenAI’s consumer focused products.
Arena Overview section is heavily biased towards languages. grok-4.1-thinking is worse than claude-opus-4-5-20251101-thinking-32k on every non-language metric by a large margin but somehow ranks higher overall, maybe because opus is way worse Spanish and Korean?