Every model on the leaderboard, one page each

1. #1Claude Opus 5.5AnthropicThe model people actually ship agents on: top of the independent index, a price that does not need a budget meeting, and a community that complains mainly about how much it has to be used.
2. #2GPT-6 AstraOpenAIThe reasoning heavyweight: leads the hardest exams and the cipher-cracking party tricks, and charges like it.
3. #3Gemini 4 ArgonGoogleWins the popularity contest: first on Arena, mid-pack on the index, and priced like a workhorse.
4. #4Claude Sonnet 5.5AnthropicThe value pick of the table: second on the index at a fifth of the Opus price, and the fastest of the top five.
5. #5GPT-6.1 SolOpenAINear-Astra intelligence at a fifth of the price, which is OpenAI's own line and, for once, the index agrees.
6. #6Claude Fable 5.1AnthropicThe specialist: Anthropic's own docs say to reach for it when Opus 5.5 at high effort still falls short, and the price says the same.
7. #7Claude Haiku 5.5AnthropicTen cents a million and, per the people using it, smarter than the other ten-cent model; mind the 100K cliff.
8. #8Muse Spark 1.3MetaThe fastest thing in the table by a distance, and the one to beat on the stress benchmark nobody else talks about.
9. #9DeepSeek Flash (4.1)DeepSeekThe reason a thousand people argued on Hacker News this week: frontier-adjacent coding for pocket change, with the caveats you would expect.
10. #10GPT-6 LunaOpenAIOpenAI's ten-cent model: the one every ChatGPT Free user now has, and the one Haiku users keep comparing themselves to.
11. #11Kimi K3MoonshotThe highest-placed open-licence model on Arena, and the one most teams have not tried yet.
12. #12Grok 4.7xAIMid-table on the index at a frontier price, with a smaller context window than everyone above it.

Looking for a head to head? See all comparisons or the pricing table.