s
April 4, 2024, 12:51 p.m. |

Simon Willison's Weblog simonwillison.net

The cost of AI reasoning over time


Karina Nguyen from Anthropic provides a fascinating visualization illustrating the cost of different levels of LLM over the past few years, plotting their cost-per-token against their scores on the MMLU benchmark.


Claude 3 Haiku currently occupies the lowest cost to score ratio, over on the lower right hand side of the chart.


Via @swyx

ai ai reasoning anthropic benchmark claude claude 3 claude 3 haiku cost generativeai haiku llm llms mmlu per plotting reasoning token visualization

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York