Pathway says architecture can matter as much as model scale
Hi, Your membership journey starts here. Get full access to premium articles, exclusive features and a growing list of member rewards. According to the researchers, their 150M-parameter model scored 29.5% pass@2 on the public ARC-AGI-1 evaluation set.
Hi, Your membership journey starts here. Get full access to premium articles, exclusive features and a growing list of member rewards.
Today, many AI tools waste computing power because of how they are designed, not because deep reasoning demands it. Amazon Web Services believes that BDH-CQ’s result is a promising step toward using advanced AI reasoning in real products more affordably.
What Happened
ARC-AGI-1, a widely used reasoning benchmark for AI systems, checks whether a system can infer an underlying rule from limited examples and apply it correctly to new inputs. On the cheap end, Qwen3 235B costs over three times more than BDH-CQ while.
According to the researchers, their 150M-parameter model scored 29.5% pass@2 on the public ARC-AGI-1 evaluation set.
It achieved this at a computed inference cost of $0.0007 per task, roughly eleven times cheaper than ChatGPT's underlying GPT 5.6 Luna (Low) model.
In this test, OpenAI's Luna model scored only slightly higher at 34.2%, yet running it still costs significantly more ($0.008 per task).
Key Details
The efficiency gap stems mainly from a structural difference in how each system actually performs reasoning during inference computations. Many reasoning AI systems generate intermediate text, adding one token after another before producing their final answers.
That price gap already includes OpenAI's recent 80% price cut on Luna, which began on July 30th of this year.
Further up the chart, Claude Opus 5 and Gemini 3.1 Pro reach 97–98% but cost around $0.5 – $0.6 per task, meaning the frontier's very top costs close to a thousand times more than.
Please logout and then login again, you will then be prompted to enter your display name.
Why It Matters
The longer that written reasoning becomes, the more it costs to run and the slower the AI responds to each request. BDH-CQ works quite differently, quietly solving problems inside its own memory instead of writing everything down first as visible text.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.
If these efficiency gains hold across larger and more difficult tasks, cost rather than raw capability could increasingly separate rival reasoning systems.
What Reports Say
Coverage of the story so far points to:
Continued reporting by TechRadar as more details emerge
