ReadingResearchRadarInvestment framework
Sign in / Sign up
← Back to reading
NewsMaterial3 min readDisconfirmAI Editorial

Anthropic Blog Author Addy Osmani: Select the Claude Model by Adjusting Effort Levels First, Then Switching Models

The Anthropic official blog proposes a model selection method: start daily coding and knowledge work with Opus 5.5 at medium effort; when hitting bottlenecks, increase effort rather than switching directly to more expensive models, because effort is a finer cost knob than model switching. The article uses self-test data from Terminal-Bench and FrontierCode to show that cheaper models at higher effort levels can match or even exceed more expensive models, and provides specific architectural advice for sub-agent allocation and mixed-model usage.

2026-11-09

In an official blog post released on November 9, Anthropic provided a clear starting recommendation: most coding and knowledge work should begin with Opus 5.5 at its default effort level. This is not because Opus 5.5 is the strongest model—Fable 5.2 holds that title—but because it sits at the optimal balance point between cost and capability. Opus 5.5 costs $4 per million input tokens and $20 per million output tokens, exactly half the price of Fable 5.2 ($8 and $40 respectively).

However, what makes this blog truly noteworthy is not the starting recommendation, but the adjustment sequence it proposes. Author Addy Osmani writes that you should adjust the effort level before switching models. Effort is a finer dial than model switching, simultaneously controlling changes in both cost and capability. Beyond the high setting, moving up one more effort level may cost as much as switching to a larger model. Conversely, dropping down one level might yield the results you need at a lower rate.

This advice is backed by specific benchmark data. On Anthropic's self-tested Terminal-Bench 3.0, the previous generation Fable 5.1 scored 58.0% at max effort, while Opus 5.5 scored 58.9% at high effort using only half the number of tokens. On FrontierCode 2.0, Fable 5.2 scored 45.3% at high effort, essentially matching Opus 5.5's 45.5% at max effort, but at roughly half the cost per task. These figures demonstrate that the relationship between cost and capability is non-linear at the task level: cheaper models at higher effort levels can catch up to or even surpass more expensive models.

Sign in / Sign up
ReadingResearchRadarInvestment framework

On SWE-bench Pro, Opus 5.5 improves by approximately 2.5 points when moving from medium to high effort, with costs increasing by about 43% (rising from 70% of the high-effort baseline to 100%). Moving from low to medium effort yields an improvement of about 5.5 points, at roughly double the cost of low effort (rising from one-third of the high-effort baseline to 70%). This implies that if you are currently bottlenecked at medium effort, trying high effort is often more cost-effective than jumping directly to Fable 5.2. You should only consider upgrading to Fable 5.2 when Opus 5.5 at high effort remains insufficient.

For scenarios requiring the mixed use of multiple models, the blog offers a core principle: place sub-agents on cheaper models, while keeping judgment calls and code editing on the main model. Sub-agents are suitable for tasks like searching files, running tests, and reading logs—errors here are easy to spot, and judgmental decisions are inherently made by the main model. When the model proves insufficient, Osmani suggests executing steps in order: first confirm whether the model can self-verify (via tests, builds, or scripts calling endpoints), then raise the effort level by one step, and finally switch to a larger model starting at a lower effort level. On an internal defect-search benchmark, Opus 5.5 acting as the main model orchestrated up to 25 Sonnet 5.5 workers to process approximately 22 million tokens of source code. This approach cost about one-third less than running Opus 5.5 alone, with scores remaining essentially flat.

Sources

  • claude.devclaude.dev Blog↗
Continue researching →