Subquadratic Launches SubQ 1.1 Small LLM with Competitive Benchmark Performance
By
EDM115
Summary
Subquadratic introduces SubQ 1.1 Small, a new LLM that balances long-context optimization with general reasoning. The model achieves strong benchmark scores including 85.4% on GPQA Diamond (near mid-tier frontier models), 89.7% pass@4 on LiveCodeBench (close to the absolute frontier), and 13% on AutomationBench Finance (competitive with strongest models). The article positions SubQ 1.1 Small as outperforming mid-tier and smaller baselines while approaching frontier model performance.
Source
Hacker NewsSubquadratic Launches SubQ 1.1 Small LLM with Competitive Benchmark Performancesubq.aiKey quotes
· 4 pulledSubQ 1.1 Small balances long-context optimization with general reasoning ability without compromise.
GPQA Diamond at 85.4% sits just below mid-tier frontier models and well above the smaller tier.
LiveCodeBench at 89.7% pass@4 is close to the absolute frontier.
AutomationBench Finance at 13% places SubQ 1.1 Small close to the strongest models on that benchmark, ahead of mid-tier and smaller baselines.
You might also wanna read
Startup Subquadratic claims faster, cheaper LLM that processes 12x more text
Subquadratic, a startup, claims to have developed a new LLM called SubQ that is faster, cheaper, and more energy-efficient than existing mod
technologyreview.com·15h agoStartup Subquadratic claims faster, cheaper LLM that processes 12x more text
Subquadratic, a startup, claims to have developed a new LLM called SubQ that is faster, cheaper, and more energy-efficient than existing mod
technologyreview.com·15h ago
FastContext-1.0: A Lightweight Repository-Exploration Subagent for LLM Coding Agents
FastContext-1.0 is a lightweight repository-exploration subagent designed for LLM coding agents. It separates the roles of repository explor
Google Introduces TurboQuant: Advanced LLM Compression Algorithm for Efficient AI Model Deployment
Google has developed TurboQuant, a new LLM compression algorithm that uses advanced theoretically grounded quantization techniques to enable
Product Hunt·3mo ago
Roofline Model for Estimating Speculative Decoding Speedup in LLM Inference
This article presents a roofline model for estimating speedup ratios from speculative decoding in large language model (LLM) inference. It a
modal.com·1d agoShopping Companion: Benchmarking and Training LLM Agents for Long-Horizon Preference-Grounded E-Commerce Tasks
LLM Stats: Platform for Comparing AI Language Models by Benchmarks, Cost, and Capabilities
LLM Stats is a platform that allows users to compare various AI language models (LLMs) across multiple dimensions including performance benc
Product Hunt·8mo agoComments
Sign in to join the conversation.
No comments yet. Be the first.