Sonnet 5.5 vs Haiku 5.5, what each one picks
Sonnet 5.5 and Haiku 5.5 lead with the same thing in 10 of 10 categories. same prompts, same repos, same defaults.
same lead in 10 of 10 categories. both on Claude Code, same prompts, same starter repos. updated Oct 18, 2026.
get the next model added to this
new models get the same prompts when they land. one email with what moved. free. read issue 1
category by category
the lead per model, Sonnet 5.5 first. ties are named, not broken.
- database
Sonnet 5.5: SQLite file, 9 of 12
Haiku 5.5: SQLite file, 7 of 12
same
- ORM
Sonnet 5.5: SQLAlchemy, 6 of 12
Haiku 5.5: SQLAlchemy, 6 of 12
same
- auth
Sonnet 5.5: Hand-rolled JWT or sessions, 12 of 12
Haiku 5.5: built its own, 11 of 11 (8 as hand-rolled JWT or sessions)
same
- deployment
Sonnet 5.5: Plain Docker, 7 of 12
Haiku 5.5: Plain Docker, 10 of 12
same
- email
Sonnet 5.5: Raw SMTP, 10 of 12
Haiku 5.5: Raw SMTP, 7 of 12
same
- payments
Sonnet 5.5: Stripe, 12 of 12
Haiku 5.5: Stripe, 11 of 11
same
- jobs
Sonnet 5.5: built its own, 10 of 10 (2 as hand-rolled queue or cron)
Haiku 5.5: built its own, 11 of 11
same
- caching
Sonnet 5.5: built its own, 12 of 12
Haiku 5.5: built its own, 12 of 12
same
- storage
Sonnet 5.5: Local disk, 10 of 12
Haiku 5.5: Local disk, 12 of 12
same
- monitoring
Sonnet 5.5: Sentry, 12 of 12
Haiku 5.5: Sentry, 5 of 12
same
run stats
Sonnet 5.5
- scored runs
- 118
- built its own
- 71 of 118 (60%)
- average run
- 38 s
- cost per run
- $0.098
Haiku 5.5
- scored runs
- 117
- built its own
- 77 of 117 (66%)
- average run
- 54 s
- cost per run
- $0.038
other comparisons
how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, raw data in runs.json.