# Epoch AI introduces an Inference Performance Index for AI chips

> Original title: We estimate that FLOP/s alone understates GB300’s inference advantage over H100 by 10×. The standard AI chip comparison misses most of wh...

- Source: Epoch AI
- Published: 2026-11-09T19:06:45.000Z
- Bad Influence: https://badinfluence.news/items/p6fzdjyw33gqqwzvbhalvhwa6
- Original: https://x.com/EpochAIResearch/status/2119869320499224965

## Summary

Epoch AI introduces the Inference Performance Index (IPI), a measure that accounts for memory bandwidth and inter-chip communication alongside compute. It says FLOP/s alone understates GB300's inference advantage over H100 by 10×. IPI scores are expressed in GB300 equivalents to compare chips directly and estimate a data center's total inference capacity.

## Post

We estimate that FLOP/s alone understates GB300’s inference advantage over H100 by 10×. The standard AI chip comparison misses most of what matters for inference.

We’re introducing the Inference Performance Index (IPI), a new measure that accounts for memory bandwidth and inter-chip communication alongside compute. These factors determine how many users or agents a chip can support simultaneously at a given output speed.

Scores in GB300 equivalents let you compare chips directly and estimate the total inference capacity of a data center, or even the world.

![Horizontal bar chart ranking AI chips by modeled inference performance index normalized to Nvidia GB300=1, showing up to 72× higher inference capacity for newer chips than Nvidia H100.](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWtJ6ZyaEAAdgEO.png&mode=thumb&exp=1794528000&sig=4562f3b800272164)