The story’s score and claims

Comments on No. 19 of 95 · Epoch AI · edition of Tuesday 10 November 2026

Inference Performance Index: changing the way we measure inference capacity

Summary

Epoch AI introduced the Inference Performance Index, which scores chips by how many simultaneous agentic requests they can serve across 50–400 tokens/s/req, in GB300 equivalents. Its model puts GB300 at about 25× H100 capacity with 2.5× the FP8 FLOP/s, and H200 HGX at 0.12 and VR200 at 2.18. The scores are speed-of-light projections from four models and ignore software maturity. A validation on Kimi K3 matched GB300 measurements at 50% of modeled performance, within about 12%.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules