George Cameron

georgewritescode

AI & ML interests

None yet

Recent Activity

liked a dataset about 2 months ago
ArtificialAnalysis/big_bench_audio
updated a dataset about 2 months ago
ArtificialAnalysis/hf-assets
View all activity

Organizations

Artificial Analysis's profile picture Social Post Explorers's profile picture

Posts 2

view post
Post
1029
Visualization of GPT-4o breaking away from the quality & speed trade-off curve the LLMs have followed thus far āœ‚ļø

Key GPT-4o takeaways
ā€£ GPT-4o not only offers the highest quality, it also sits amongst the fastest LLMs
ā€£ For those with speed/latency-sensitive use cases, where previously Claude 3 Haiku or Mixtral 8x7b were leaders, GPT-4o is now a compelling option (though significantly more expensive)
ā€£ Previously Groq was the only provider to break from the curve using its own LPU chips. OpenAI has done it on Nvidia hardware (one can imagine the potential for GPT-4o on Groq)

šŸ‘‰ How did they do it? Will follow up with more analysis on this but potential approaches include a very large but sparse MoE model (similar to Snowflake's Arctic) and improvements in data quality (likely to have driven much of Llama 3's impressive quality relative to parameter count)

Notes: Throughput represents the median across providers over the last 14 days of measurements (8x per day)

Data is present on our HF leaderboard: ArtificialAnalysis/LLM-Performance-Leaderboard and graphs present on our website

Articles 3

Article
17

Evaluating Audio Reasoning with Big Bench Audio

models

None public yet

datasets

None public yet