Edition of Wednesday 11 November 2026

Which Claude model should you build with? Fable, Opus, Sonnet, or Haiku

Comments on “Which Claude model should you build with? Fable, Opus, Sonnet, or Haiku”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

This Claude model guide advises most builders to start with Opus 5.5 at medium effort, since it costs half as much per token as Fable 5.2. It recommends Sonnet 5.5 for well-scoped work, Haiku 5.5 for high-volume simple tasks, and Fable 5.2 for the hardest technical projects.

Read the original at claude.dev. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 55 of 143 with a score of 0.64. The panel rated it highest on practical relevance (0.91) and technical depth (0.80), lowest on significance (0.56). The judges disagreed most on new information (spread 0.49), so the story is marked contested. Placed No. 55, No. 48 by score alone: the 20th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Practical guidance on choosing among AI model tiers with concrete pricing and trade-offs, highly relevant to builders, but largely vendor-authored promotional guidance with unverified claims and heavy product-marketing framing.
AI judgeJudge 3gpt-5.6-luna
A detailed model-selection and migration guide with pricing, effort, compatibility, orchestration, benchmarks, and concrete configuration advice. It is highly actionable, though vendor-authored claims and internal benchmarks make it somewhat promotional and less independently substantiated.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.64total under rubric v2.3Contestedjudges differ by 0.49 on new information

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.56
  • Reader interest0.76
  • Audience breadth0.66
  • Practical relevance0.91
  • Substantiated0.72
  • Technical depth0.80
  • New information0.74
  • Counts against: Promotional0.34
  • Counts against: Overclaim0.23

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.670.350.670.560.32+0.24+0.135
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.720.700.860.760.16+0.26+0.198
Audience breadthHow many people who build technology does it concern?0.500.670.820.660.32+0.13+0.086
Practical relevanceHow useful is it to someone who builds software or tech products?0.980.850.910.910.13+0.22+0.201
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.900.550.720.720.35+0.05+0.036
Technical depthHow technically substantive is it?0.950.700.750.800.25+0.05+0.040
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.840.450.940.740.49 , above the contested threshold+0.05+0.037
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.140.450.420.340.31−0.19−0.064
OverclaimDo the headline or conclusions claim more than the body supports?0.220.300.180.230.12−0.11−0.026
Sum of contributions+0.644
Claim-check penalty0.000
Total, as published0.644

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #55 on Rubric, 11 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-11/55/"><img src="https://rubric.hrih.si/badge/2026-11-11/55.svg" alt="Ranked #55 on Rubric, 11 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 11 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Which Claude model should you build with? Fable, Opus, Sonnet, or Haiku”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.75

    llama.cpp v1.0