← Back to KHAO

Compute ·

AutomationBench Finance at 13% places SubQ 1.1 Small close to the strongest models on that benchmark

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

◌ Single Source

Compute comparison: dense O(n²) attention reaches 252 PFLOP per layer at 1M tokens, while SubQ's SSA O(n) attention stays near-flat — up to 64× less compute.

SSA replaces the O(n²) dense attention pass with a learned sparse formulation that scales linearly with context length.

Key facts

Summary

For years, the industry worked around this problem by building retrieval pipelines, chunking strategies, and agentic scaffolding, useful tools, but ultimately workarounds for context limitations of the model architecture. SubQ is built to remove that constraint. Near-perfect long-context retrieval up to 12M tokens on the needle-in-a-haystack test, with up to nearly 1,000x attention compute reduction. A balance of long-context optimization and general reasoning ability, with strong performance retained across knowledge, coding, and non-coding enterprise agent benchmarks. At 1M tokens, SubQ 1.1 Small requires 64.5x less compute than dense attention and runs 56x faster than FlashAttention-2.

Read full article at subq.ai →

#Compute