@artificialanalysis.bsky.social
Llama 3.3 70B takes a leap forward on all evals we benchmark.
It now leads Llama 3.1 405B in MATH and almost matches 405B in each of MMLU, GPQA Diamond and HumanEval.
It now leads Llama 3.1 405B in MATH and almost matches 405B in each of MMLU, GPQA Diamond and HumanEval.
December 6, 2024 at 8:37 PM
Llama 3.3 70B takes a leap forward on all evals we benchmark.
It now leads Llama 3.1 405B in MATH and almost matches 405B in each of MMLU, GPQA Diamond and HumanEval.
It now leads Llama 3.1 405B in MATH and almost matches 405B in each of MMLU, GPQA Diamond and HumanEval.
Meta launches Llama 3.3 70B, achieving a level of intelligence previously reserved for Llama 3.1 405B and leapfrogging the November release of GPT-4o
We have completed our first round of evals on Llama 3.3 70B and are seeing a jump in our Quality Index from 68 to 74, now matching Llama 3.1 405B.
We have completed our first round of evals on Llama 3.3 70B and are seeing a jump in our Quality Index from 68 to 74, now matching Llama 3.1 405B.
December 6, 2024 at 8:37 PM
Meta launches Llama 3.3 70B, achieving a level of intelligence previously reserved for Llama 3.1 405B and leapfrogging the November release of GPT-4o
We have completed our first round of evals on Llama 3.3 70B and are seeing a jump in our Quality Index from 68 to 74, now matching Llama 3.1 405B.
We have completed our first round of evals on Llama 3.3 70B and are seeing a jump in our Quality Index from 68 to 74, now matching Llama 3.1 405B.
Artificial Analysis Video Arena update - MiniMax's Hailuo AI continues to lead with Genmo's Mochi 1 coming in a close second and holding the title of leading open source video generation model.
November 20, 2024 at 9:54 AM
Artificial Analysis Video Arena update - MiniMax's Hailuo AI continues to lead with Genmo's Mochi 1 coming in a close second and holding the title of leading open source video generation model.