Understand this story
Subquadratic releases decision model SubQ Snap 1.1. According to Artificial Analysis, the model scores 65 on the Artificial Analysis Decision Index v1.0, tying for first place with d1-ultra and Elephant 9B, and leading third-place Jev 1.14 (57 points) by 8 points. Its non-hallucination rate is 86%, second only to Elephant 9B's 93% and higher than d1-ultra's 85%; accuracy is 20%, and it scores 18% on HLE-MultiChoice. Input price is $0.04 per 1 million tokens, context window is 384K, and cost per 1 million tasks is $30, about 3.6 times that of the equally scoring Elephant 9B ($8.4). There are currently no subsequent development facts.
AI-generated from public reports
Latest development · Report
Subquadratic releases the SubQ Snap 1.1 decision modelDevelopments
1 confirmed developments
- Source:Artificial Analysis
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
Artificial Analysis
Subquadratic releases the SubQ Snap 1.1 decision model
Subquadratic releases the decision model SubQ Snap 1.1, which scores 65 on the Artificial Analysis Decision Index v1.0, tying for first place with d1-ultra and Elephant 9B and leading the third-place Jev 1.14 (57) by 8 points. Its non-hallucination rate is 86%, second only to Elephant 9B's 93% and higher than d1-ultra's 85%; its accuracy is 20%, and it scores 18% on HLE-MultiChoice. Input pricing is $0.04/1M tokens, the context window is 384K, and the cost per 1M tasks is $30, about 3.6 times that of the equally scoring Elephant 9B ($8.4).