How fast is Rocket.new?

The median turn latency is 107.2 seconds per prompt, not per whole build, which derives to 16.1 min across the full nine prompt specification. That is a tenth percentile of 53.3 seconds and a ninetieth percentile of 217.0 seconds across 45 recorded executions.

How reliable is Rocket.new?

60.0% of recorded executions met the published pass criterion with no operator intervention. 7 were partial and 11 failed outright. Every one of those rows is published on this page.

Can I export the code from Rocket.new?

Partial. The code ownership subscore is 58.0 out of 100.

Full-stack app builders / rank 14 of 20 / cycle 04

Rocket.new benchmark

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.

Last run: 15 Aug 2026 09:11 UTCNext scheduled run: n/aOfficial site Rocket.new reviews and ratings

Composite index

62.12

of 100 | withheld vs. cycle 03

Delta not shown for cycle 04: the roster was re-based from one merged ranking into two class boards, so cycle 03 and cycle 04 ranks are not on the same scale. Resumes cycle 05.

At a glance

Composite index

62.12

rank 14 of 20

Rank

#14

of 20 on the full-stack app builders board

Median turn latency

107.2 s per prompt

16.1 min across the full nine prompt spec, derived

Reliability

60.0%

strict pass rate

SEO score

57.0

0 to 100, SEO and GEO axis

Three strongest axes

Design output75.0
Agent performance70.0
Value66.0

Three weakest axes

API and MCP52.0
SEO and GEO57.0
Code ownership58.0

Median turn latency

107.2 s per prompt

p10 53.3 s, p90 217.0 s

Strict pass rate

60.0%

27 pass, 7 partial, 11 fail

Executions recorded

5 runs of 9 prompts

Entry price

USD 25 / month

Vendor's own unit and billing period. Never a currency conversion

Per axis subscores

Composite recomputed from these 10 rows: 62.12. That is the arithmetic behind the index, and you can repeat it by hand. Rounding rule: half up at two decimals, applied uniformly to all 37 published products.

Weight table

Per axis subscores against the roster median, and weighted contribution
Axis	Score	Median	Weight %	Contribution
Agent performance	70.0	71.5	18	12.60
Reliability	60.0	71.1	18	10.80
Scalability	61.0	66.0	13	7.93
SEO and GEO	57.0	63.5	12	6.84
API and MCP	52.0	58.0	9	4.68
Integrations	59.0	65.0	8	4.72
Design output	75.0	78.5	7	5.25
Turn latency score	60.8	66.5	7	4.26
Value	66.0	74.0	5	3.30
Code ownership	58.0	73.0	3	1.74

Turn latency distribution

Every recorded prompt duration for Rocket.new, in seconds. Median wall clock time for one prompt, not for a whole build. The cyan tick on the whisker is the median.

min 36.3 smax 294.7 s

Spread against the cohort

p10 53.3 s / median 107.2 s / p90 217.0 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 2.02x.

Outcome split

27 pass / 7 partial / 11 fail

SEO and GEO measurements

Taken from the public marketing page this product generated in prompt 8, fetched with JavaScript disabled.

SEO and GEO leaderboard

HTML bytes, no JS

7.0 KB

7,168 bytes of real text content with scripts blocked

LCP

3,260 ms

Throttled connection, cold cache

CLS

0.160

Cumulative layout shift on load

SEO and GEO subscore

57.0

0 to 100, worth 12 index points on this board

Raw run data: 45 executions

One row per prompt execution. Nothing is aggregated away, nothing is hidden, including the failures.

JSON

Raw per run measurements
Run	Prompt	Prompt target	Started	Duration (s)	Outcome	Note
R01	P01	Tenant and user model	11 Aug 2026 08:00 UTC	106.6	pass
R01	P02	Authentication and session	11 Aug 2026 08:03 UTC	93.0	partial	Validation added on the write path only. Read path left unguarded.
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:07 UTC	78.5	fail	Agent looped on the same edit for the full timeout window of 20 minutes.
R01	P04	Public REST API with keys	11 Aug 2026 08:10 UTC	214.8	partial	Pagination off by one at the final page boundary.
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:16 UTC	71.6	fail	No signature on outbound webhooks and no delivery history stored. Retry ladder absent.
R01	P06	Background jobs	11 Aug 2026 08:19 UTC	113.5	pass
R01	P07	Admin panel	11 Aug 2026 08:23 UTC	145.9	pass
R01	P08	Public marketing surface	11 Aug 2026 08:27 UTC	120.6	fail	Build did not start after deploy. Recorded as a fail with the log preserved.
R01	P09	Hardening pass	11 Aug 2026 08:31 UTC	188.9	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	86.8	pass
R02	P02	Authentication and session	12 Aug 2026 08:03 UTC	74.2	pass
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:06 UTC	222.2	fail	Agent looped on the same edit for the full timeout window of 20 minutes.
R02	P04	Public REST API with keys	12 Aug 2026 08:12 UTC	75.2	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:15 UTC	107.2	fail	No signature on outbound webhooks and no delivery history stored. Retry ladder absent.
R02	P06	Background jobs	12 Aug 2026 08:19 UTC	96.6	pass
R02	P07	Admin panel	12 Aug 2026 08:23 UTC	70.1	pass
R02	P08	Public marketing surface	12 Aug 2026 08:26 UTC	36.3	pass
R02	P09	Hardening pass	12 Aug 2026 08:28 UTC	81.2	pass
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	153.3	partial	Pagination off by one at the final page boundary.
R03	P02	Authentication and session	13 Aug 2026 08:04 UTC	151.1	pass
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:09 UTC	191.6	fail	Deployed URL returned 500 on every request.
R03	P04	Public REST API with keys	13 Aug 2026 08:14 UTC	105.9	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:18 UTC	153.0	fail	No signature on outbound webhooks and no delivery history stored. Retry ladder absent.
R03	P06	Background jobs	13 Aug 2026 08:22 UTC	54.9	pass
R03	P07	Admin panel	13 Aug 2026 08:25 UTC	131.9	pass
R03	P08	Public marketing surface	13 Aug 2026 08:29 UTC	71.6	pass
R03	P09	Hardening pass	13 Aug 2026 08:32 UTC	125.0	pass
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	52.3	pass
R04	P02	Authentication and session	14 Aug 2026 08:02 UTC	65.5	pass
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:05 UTC	218.5	partial	Validation added on the write path only. Read path left unguarded.
R04	P04	Public REST API with keys	14 Aug 2026 08:11 UTC	133.7	fail	Generated migration conflicted with the existing schema and was not reconciled.
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:15 UTC	179.6	fail	No signature on outbound webhooks and no delivery history stored. Retry ladder absent.
R04	P06	Background jobs	14 Aug 2026 08:20 UTC	184.8	pass
R04	P07	Admin panel	14 Aug 2026 08:25 UTC	55.0	fail	Deployed URL returned 500 on every request.
R04	P08	Public marketing surface	14 Aug 2026 08:28 UTC	38.6	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R04	P09	Hardening pass	14 Aug 2026 08:31 UTC	40.6	pass
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	41.3	pass
R05	P02	Authentication and session	15 Aug 2026 08:02 UTC	122.5	pass
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:06 UTC	231.6	pass
R05	P04	Public REST API with keys	15 Aug 2026 08:12 UTC	66.5	partial	Error envelope inconsistent between two of the endpoints.
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:15 UTC	294.7	fail	No signature on outbound webhooks and no delivery history stored. Retry ladder absent.
R05	P06	Background jobs	15 Aug 2026 08:22 UTC	261.6	pass
R05	P07	Admin panel	15 Aug 2026 08:28 UTC	154.2	partial	Validation added on the write path only. Read path left unguarded.
R05	P08	Public marketing surface	15 Aug 2026 08:33 UTC	81.0	pass
R05	P09	Hardening pass	15 Aug 2026 08:36 UTC	155.6	pass

Pricing

Credit based with a small free allowance. Paid plans from USD 25 per month.

Pricing note

Rocket describes each tier as a monthly platform fee quoted with a bare dollar sign, and states no currency anywhere on its pricing page. USD is this lab's reading, not a vendor statement, and the euro figure follows from it.

Entry price: USD 25 / month
Priced from: vendor pricing page
Value subscore: 66.0
Index points per euro: 2.91

Entry price is the vendor's own published figure, fetched 21 Aug 2026, never a currency conversion. The currency label is the vendor's own except where the pricing note above records that this lab inferred it. Index points per euro is computed from a separate, euro-normalised figure used only for the Value axis: Converted at the European Central Bank euro reference rate of 1.1699 US dollars to the euro, August 21, 2026.

Capabilities as measured

stack: React front end with a managed backend
deploy: Hosted deploy
database: Built in collections
auth: Built in
background jobs: Partial, timer based
webhooks: Outbound only, unsigned
rest api: Generated, no key management
mcp server: No
export code: Partial
custom domain: Yes on paid plans
ssr: Client rendered

Screenshot

Rocket.new landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.

Rocket.new landing page, captured by the lab at 1440 by 900

Rocket.new, captured 14 Aug 2026.

Sources and fetch dates

Every claim on this page traces to one of these.

Sources with fetch dates
Source	URL	Fetched
Rocket.new pricing page	https://rocket.new/pricing	14 Aug 2026
Rocket.new product site	https://rocket.new	14 Aug 2026
LLM Tier run harness output	https://www.llm-tier.com/api/runs.json	14 Aug 2026

Rich results carry this composite as 3.1 on a 0 to 5 scale because that is the only scale the format accepts. The number on this page, 0 to 100, is the real one.

Rocket.new head to head

zite vs rocket-new

Reader index

Voted by readers with an account, one score per person per axis. Published beside the lab index, never inside it.

Score it or read the notes

Reader index

not rated yet

Lab index

62.12

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

Seeded at launch

The reader scores, lab notes and open ratings published here were written by this lab in August 2026 to populate the reader column before the site had readers. They are not customer submissions, they are not vendor supplied and nobody was paid for them. Anything submitted since then comes from a registered account. The lab index is measured from logged runs and is unaffected either way.

Reader mean against the measured lab subscore for each axis
Axis	Weight	Lab	Readers	Votes
Agent performance	18%	70.0	63.0	1
Reliability	18%	60.0	52.0	1
Scalability	13%	61.0	54.0	1
SEO and GEO	12%	57.0	54.0	1
API and MCP	9%	52.0	35.0	1
Integrations	8%	59.0	52.0	1
Design output	7%	75.0	69.0	1
Turn latency score	7%	60.8	15.0	1
Value	5%	66.0	57.0	1
Code ownership	3%	58.0	46.0	1

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.

Open rating mean

63.50

2 published open ratings, submitted without an account

Lab index

62.12

Measured, not voted

Gap to the measurement

1.38

Positive means open raters put it above the measurement

What agent performance looked like in practice

Across 45 recorded executions this product met the published pass criterion cleanly 27 times, partially 7 times and failed 11 times. The rows above carry the reviewer note for every non clean outcome, which is the only way to tell a product that fails loudly from one that fails quietly.