Expired50% confidenceBenchmarkExact time
Mozilla's State of Open Source AI report, based on Chatbot Arena data, shows that the average capability gap between open-weight models and closed-source models has narrowed to 3.3%, significantly down from 8.04% in January 2024.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
Valid until: 10/19/2026(expired)
Sources
Related Claims
UnverifiedThe performance gap in code capabilities between open-source and closed-source models is being rapidly narrowed.66% similarUnverifiedThe performance gap among flagship models from OpenAI, Anthropic, Google, DeepSeek, and other vendors on mainstream benchmarks is narrowing.66% similarUnverifiedDuring evaluation, in order to measure the upper bound of the model's underlying capabilities, OpenAI temporarily disabled the model's outer filters, i.e., "lowered the cybersecurity refusal rate."65% similarUnverifiedThe capabilities of open-source models (such as the Llama series) have significantly narrowed the gap with commercial models.64% similarUnverifiedOpenAI在2019年的研究中证实双重下降现象同时存在于模型复杂度、训练时间和样本数量三个维度64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/577595API
curl https://kongchang.com/api/v1/knowledge/claims/577595MCP
get_claim(id=577595)