Study: best AI models outside the US and China lag the US by nearly a year
Understand this story
Village used its LLM Atlas to compare 857 models on the same capability scale and found that since 2024, each new best model outside the United States and China had a median lag of 9.9 months relative to the best US model, never less than 7.3 months; China's median lag was 5.2 months. The conclusion is based on scores as of October 31, 2026, and Atlas will update as new results come in. Village noted that Atlas has less coverage of models before 2023, so the comparison underlying the early-2024 gap is thinner; its benchmark is mainly English and may underestimate models built for languages such as Korean, Arabic, and Indian languages; India's figure is based on only two Sarvam models.
AI overview based on source reports · Updated 12 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIAI models built outside the US and China are nearly a year behind
Village's LLM Atlas, which scores 857 models on one capability scale, finds that since 2024 the best models from outside the US and China have trailed US models by a median of 9.9 months, versus 5.2 months for China. South Korea and Mistral are closest at about 10 months behind, while India's Sarvam 30B scores where US models were 28 months earlier. Labs outside the two countries released about 20 of the models Atlas ranks from 2026, against 113 from the US and 79 from China.
Activity for this story
Not enough continuous observations to show a trend yet.