News for hackers. Stuff that matters.
Re:OpenAI slashes the cost of using its AI with a "mini" model by pzo on Thursday July 18, 2024 @03:01PM (#40998689)
Also for some reference:

Gemma 2 27B scored: 75.2 in MMLU

LLama 3 70B scored: 79.5 in MMLU

Haiku scored: 75.2 in MMLU

GPT 3.5 scored: 70.0 in MMLU

Based on pricing I see in openrouter.ai across different providers this seems like the cheapest model for this kind of performance.

ref: [0] https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bb...

[1] https://blog.google/technology/developers/google-gemma-2/

There are no comments on this comment yet.