The median turn latency is 135.7 seconds per prompt, not per whole build, which derives to 20.4 min across the full nine prompt specification. That is a tenth percentile of 92.8 seconds and a ninetieth percentile of 188.8 seconds across 45 recorded executions.

How reliable is Replit?

86.7% of recorded executions met the published pass criterion with no operator intervention. 4 were partial and 2 failed outright. Every one of those rows is published on this page.

Can I export the code from Replit?

Full filesystem access and Git. The code ownership subscore is 82.0 out of 100.

Full-stack app builders / rank 5 of 20 / cycle 04

Replit benchmark

The most operationally complete result: a real queue, working scheduled jobs and a database that survived the 50000 row load without a rewrite. It is also the slowest of the top group because the agent runs a longer plan and test cycle. The public marketing surface was the weakest part, client rendered in 4 of 5 runs.

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

Composite index

75.47

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

75.47

rank 5 of 20

Rank

of 20 on the full-stack app builders board

Median turn latency

135.7 s per prompt

20.4 min across the full nine prompt spec, derived

Reliability

86.7%

strict pass rate

SEO score

62.0

0 to 100, SEO and GEO axis

Three strongest axes

Reliability86.7
Agent performance83.0
Code ownership82.0

Three weakest axes

Turn latency score48.0
SEO and GEO62.0
API and MCP71.0

Median turn latency

135.7 s per prompt

p10 92.8 s, p90 188.8 s

Strict pass rate

86.7%

39 pass, 4 partial, 2 fail

Executions recorded

5 runs of 9 prompts

Entry price

USD 20 / month, billed monthly

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

Per axis subscores

Composite recomputed from these 10 rows: 75.47. 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	83.0	71.5	18	14.94
Reliability	86.7	71.1	18	15.61
Scalability	80.0	66.0	13	10.40
SEO and GEO	62.0	63.5	12	7.44
API and MCP	71.0	58.0	9	6.39
Integrations	77.0	65.0	8	6.16
Design output	73.0	78.5	7	5.11
Turn latency score	48.0	66.5	7	3.36
Value	72.0	74.0	5	3.60
Code ownership	82.0	73.0	3	2.46

Turn latency distribution

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

min 68.2 smax 214.6 s

Spread against the cohort

p10 92.8 s / median 135.7 s / p90 188.8 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.39x.

Outcome split

39 pass / 4 partial / 2 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

9.0 KB

9,216 bytes of real text content with scripts blocked

LCP

2,880 ms

Throttled connection, cold cache

CLS

0.120

Cumulative layout shift on load

SEO and GEO subscore

62.0

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	108.5	pass
R01	P02	Authentication and session	11 Aug 2026 08:03 UTC	95.6	pass
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:07 UTC	85.9	pass
R01	P04	Public REST API with keys	11 Aug 2026 08:10 UTC	176.1	pass
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:15 UTC	122.9	pass
R01	P06	Background jobs	11 Aug 2026 08:19 UTC	104.6	pass
R01	P07	Admin panel	11 Aug 2026 08:23 UTC	94.7	pass
R01	P08	Public marketing surface	11 Aug 2026 08:27 UTC	192.7	pass
R01	P09	Hardening pass	11 Aug 2026 08:32 UTC	102.4	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	91.5	pass
R02	P02	Authentication and session	12 Aug 2026 08:03 UTC	109.9	pass
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:07 UTC	89.9	pass
R02	P04	Public REST API with keys	12 Aug 2026 08:10 UTC	169.6	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:15 UTC	172.3	pass
R02	P06	Background jobs	12 Aug 2026 08:20 UTC	197.4	pass
R02	P07	Admin panel	12 Aug 2026 08:25 UTC	77.0	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R02	P08	Public marketing surface	12 Aug 2026 08:29 UTC	100.7	pass
R02	P09	Hardening pass	12 Aug 2026 08:32 UTC	182.9	pass
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	123.9	pass
R03	P02	Authentication and session	13 Aug 2026 08:04 UTC	127.9	pass
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:08 UTC	141.0	pass
R03	P04	Public REST API with keys	13 Aug 2026 08:12 UTC	169.9	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:17 UTC	175.8	fail	Generated migration conflicted with the existing schema and was not reconciled.
R03	P06	Background jobs	13 Aug 2026 08:22 UTC	178.3	partial	Required one clarifying instruction before the criterion was met.
R03	P07	Admin panel	13 Aug 2026 08:27 UTC	149.4	pass
R03	P08	Public marketing surface	13 Aug 2026 08:31 UTC	174.0	pass
R03	P09	Hardening pass	13 Aug 2026 08:36 UTC	150.0	pass
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	116.2	pass
R04	P02	Authentication and session	14 Aug 2026 08:03 UTC	139.3	pass
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:08 UTC	135.7	pass
R04	P04	Public REST API with keys	14 Aug 2026 08:12 UTC	126.9	pass
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:16 UTC	139.5	pass
R04	P06	Background jobs	14 Aug 2026 08:20 UTC	214.6	pass
R04	P07	Admin panel	14 Aug 2026 08:26 UTC	101.9	pass
R04	P08	Public marketing surface	14 Aug 2026 08:30 UTC	144.1	pass
R04	P09	Hardening pass	14 Aug 2026 08:34 UTC	115.6	pass
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	106.0	pass
R05	P02	Authentication and session	15 Aug 2026 08:03 UTC	201.6	pass
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:09 UTC	96.6	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R05	P04	Public REST API with keys	15 Aug 2026 08:12 UTC	155.9	pass
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:17 UTC	117.7	partial	Pagination off by one at the final page boundary.
R05	P06	Background jobs	15 Aug 2026 08:21 UTC	172.4	pass
R05	P07	Admin panel	15 Aug 2026 08:26 UTC	137.5	fail	Generated migration conflicted with the existing schema and was not reconciled.
R05	P08	Public marketing surface	15 Aug 2026 08:30 UTC	199.1	pass
R05	P09	Hardening pass	15 Aug 2026 08:35 UTC	68.2	pass

Pricing

Free tier for prototypes. Core from USD 20 per month including agent time, deployments and always on services.

Entry price: USD 20 / month, billed monthly
Priced from: vendor pricing page
Value subscore: 72.0
Index points per euro: 4.41

Entry price is the vendor's own published figure, fetched 08 Sep 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: Any, a full Linux workspace
deploy: Autoscale, reserved VM and scheduled deployments
database: Built in Postgres and key value store
auth: Built in identity plus libraries
background jobs: Yes, scheduled deployments and workers
webhooks: Hand written, full control
rest api: Hand written, full control
mcp server: Yes
export code: Full filesystem access and Git
custom domain: Yes
ssr: Depends on the framework the agent picks

Screenshot

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

Replit landing page, captured by the lab at 1440 by 900

Replit, 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
Replit pricing page	https://replit.com/pricing	14 Aug 2026
Replit product site	https://replit.com	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 3.8 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.

Replit head to head

replit vs bolt-new lovable vs replit emergent vs replit

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

67.02

Lab index

75.47

3 readers, 25 axis scores, last change 31 Aug 2026. Readers rate Replit 8.4 points below the measurement.

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%	83.0	73.0	3
Reliability	18%	86.7	80.3	3
Scalability	13%	80.0	72.7	3
SEO and GEO	12%	62.0	57.7	3
API and MCP	9%	71.0	64.3	3
Integrations	8%	77.0	72.3	3
Turn latency score	7%	48.0	18.7	3
Value	5%	72.0	66.0	1
Code ownership	3%	82.0	72.7	3

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

79.50

2 published open ratings, submitted without an account

Lab index

75.47

Measured, not voted

Gap to the measurement

4.03

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 39 times, partially 4 times and failed 2 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.