Yea, it’s Terra 6.1 and Sonnet 5.5 level performance, per the benchmarks. Like you, I was left wondering whether this was better or worse than Argon, etc. It’s not intuitive; gotta read the fine print.

▲

throwaway473825 a day ago | parent | next [-]

According to Artificial Analysis, Gemini 4 Hydrogen (54) is closer to GPT-6.1 Sol (55) than GPT-6.1 Terra (51). Interestingly, it's also better than Gemini 4 Argon (50), which was Google's previous Pro model. Claude Sonnet 5.5 (55) is slightly ahead though.

▲

busssard 14 hours ago | parent | prev [-]

Google - gas molecule size

anthropic - prose length

openAI - heavenly body size

xAI - grok

	▲	tym0 4 hours ago \| parent [-]
		Except Google's is elements not molecules, and their atomic size has nothing to do with their performance. At least Anthropic's and Openai's make sense.