The US-China model gap is very uncertain.
Gap (months)
Chinese frontier release
US frontier release
excludes LLaMA-65B and Baichuan1-7B per Epoch's methodology
Sidequest Note · Parv Mahajan ·
The US-China AI gap is very uncertain.
We visualize, at each Chinese model release, how many months before that US frontier models reached that capability level — measured against the Epoch Capabilities Index, held flat between releases.
Frontier release timeline
Two charts in circulation imply overconfident conclusions.
Two recent visualizations frame the US-China model gap in opposite directions. The U.S. Center for AI Standards and Innovation's evaluation of DeepSeek V4 Pro fits parallel Elo-vs-time trend lines for U.S. and PRC frontier models, suggesting a steadily widening U.S. lead and that Chinese labs are structurally unlikely to close it. Epoch AI's analysis of the Epoch Capabilities Index instead tracks each frontier release as a step function and reads the gap as roughly stable, or modestly narrowing.
We believe both readings overstate the confidence that the underlying data can support. Reasonable choices about which models count as “frontier,” which of these models are measured, and which benchmarks to include in a composite produce qualitatively different conclusions. We provide a visualization that we believe more accurately captures this uncertainty. Our best guess is that Chinese models are 3 - 9 months behind the US frontier.