Rocket.new logo

Opinion page / measured product / rank 32

Rocket.new Reviews and Ratings (2026)

Reader ratings for Rocket.new, aggregated on the same 0 to 100 scale we use for the lab index, with our own commentary underneath. If you are looking for Rocket.new opiniones, reviews or a rating you can check, the measurements behind every claim are on the Rocket.new benchmark page.

Reader index

not rated yet

1 voters, 10 axis scores. Never blended into the lab index.

Lab index

60.16

Measured on the vibeOps spec

Strict pass rate

60.0%

27 clean and 11 failed executions

Median per prompt

107.2 s

p90 217.0 s

Reader index

One score per reader per axis on a 0 to 100 scale, editable at any time.

Reader index

not rated yet

Lab index

60.16

1 readers have scored 100% of the index weight so far. A reader index is published at 3 voters and 50% coverage.

Reader mean against the measured lab subscore for each axis
AxisWeightLabReadersVotesReader mean
Agent performance18%70.063.01
Reliability18%60.052.01
Scalability13%61.054.01
SEO and GEO12%57.054.01
API and MCP9%52.035.01
Integrations8%59.052.01
Design output7%75.069.01
Speed7%29.315.01
Value5%71.057.01
Code ownership3%58.046.01

The reader index is a weighted mean of reader submitted axis scores using the published index weights, renormalised over the axes readers have scored. It is never blended into the lab index. How this works.

Score Rocket.new

Your scores feed the reader column only. Submitting an axis again edits your existing score rather than adding a second vote.

Reader scores need an account so one person cannot vote twice. Create a reader account or sign in.

Reader scores are published in a separate reader index column. They never move the measured lab index.

Reader lab notes on Rocket.new

Written by readers with an account. Sorted by upvotes, then by date.

  • Fine for a booking form, wrong for anything with an operator

    Ole Jacobsen | 08 Aug 2026

    I was brought in to finish a project built on it, which is the least flattering possible way to meet a product. Judged on what it is for, a small application with a few forms and a light data model, it did the job and the client was happy. Judged on the spec this site runs it falls over exactly where the lab says it does. The outbound webhooks signed nothing at all, there was no record of what had been sent, and the retry behaviour was to not retry. I could not honestly score API and MCP above twenty, and the low reliability figure published here matches what I found.

Write a lab note

What you built, what broke, what you measured. Short opinions belong in the open rating form further down.

Sign in to publish a lab note. Notes need at least 240 characters because a one line opinion is not evidence.

Open rating distribution

Open ratings submitted without an account. Neither the lab index nor the reader index is part of this average.

Reader rating distribution
BandShareRatings
90 to 1000
80 to 890
70 to 790
60 to 692
0 to 590

Lab commentary

Our reading of the numbers, kept separate from the reader ratings.

Comfortable with the first four prompts and visibly out of depth after that. Webhook signing was absent in every run and the job queue in prompt 6 was a cron style loop with no idempotency, which the replay test caught immediately.

On the measured axes, Rocket.new is strongest at design output with a subscore of 75.0 and weakest at speed at 29.3. Because speed carries 7 of the 100 index points, that weakness costs it roughly 4.95 points against a perfect result on that axis alone.

Reader ratings and lab measurements answer different questions. A reader rating carries the thing a harness cannot capture: whether the product was pleasant to work with over weeks, how support behaved, whether the bill matched the plan. The lab index carries the thing an opinion cannot: 45 timed executions of the same specification with the failures counted. Read them side by side and treat a large gap between the two as the interesting signal.

2 open ratings

Newest first, no account needed. Moderated for spam and vendor astroturfing, not for sentiment.

  • Struggles past the basics

    Alicia Gomez, Junior developer | 13 Aug 2026

    61

    The moment I asked for webhooks it produced something that did not sign anything.

  • Fine for simple apps

    Peter Nagy, Small business owner | 08 Aug 2026

    66

    Did what I needed for a booking tool. I would not build a platform on it.

Add an open rating

No account needed. For a score that counts toward the reader index, use the axis form above.

Rate Rocket.new

One rating per person per product, on the same 0 to 100 scale as the lab index. Ratings without a body are discarded. We publish the name you enter, so use what you are happy to see in public.