The median turn latency is 72.4 seconds per prompt, not per whole build, which derives to 10.9 min across the full nine prompt specification. That is a tenth percentile of 49.1 seconds and a ninetieth percentile of 140.4 seconds across 45 recorded executions.

How reliable is Kiro?

93.3% of recorded executions met the published pass criterion with no operator intervention. 2 were partial and 1 failed outright. Every one of those rows is published on this page.

Coding agents / rank 3 of 17 / cycle 04

Kiro benchmark

Writes a specification and a task list before it writes code, which costs it roughly a third more wall clock than the fastest agents and buys back one of the tightest duration spreads in the index. The specification step is why prompt 2 came out correct in five of five runs: the tenancy rule was written down before anything depended on it.

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

Composite index

75.67

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

75.67

rank 3 of 17

Rank

of 17 on the coding agents board

Median turn latency

72.4 s per prompt

10.9 min across the full nine prompt spec, derived

Reliability

93.3%

strict pass rate

SEO score

60.0

0 to 100, SEO and GEO axis

Three strongest axes

Reliability93.3
Agent performance84.0
Scalability80.0

Three weakest axes

Turn latency score43.4
SEO and GEO60.0
Design output65.0

Median turn latency

72.4 s per prompt

p10 49.1 s, p90 140.4 s

Strict pass rate

93.3%

42 pass, 2 partial, 1 fail

Executions recorded

5 runs of 9 prompts

Entry price

USD 20 / user / month

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

Per axis subscores

Composite recomputed from these 9 rows: 75.67. 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. Code ownership has no row here: it is not scored on this board.

Weight table

Per axis subscores against the roster median, and weighted contribution
Axis	Score	Median	Weight %	Contribution
Reliability	93.3	75.6	18.56	17.32
Agent performance	84.0	80.0	18.55	15.58
Scalability	80.0	74.0	13.4	10.72
SEO and GEO	60.0	56.0	12.37	7.42
API and MCP	72.0	70.0	9.28	6.68
Integrations	74.0	70.0	8.25	6.11
Design output	65.0	62.0	7.22	4.69
Turn latency score	43.4	39.9	7.22	3.13
Value	78.0	80.0	5.15	4.02

Turn latency distribution

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

min 26.5 smax 254.4 s

Spread against the cohort

p10 49.1 s / median 72.4 s / p90 140.4 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.94x.

Outcome split

42 pass / 2 partial / 1 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

22.0 KB

22,528 bytes of real text content with scripts blocked

LCP

1,800 ms

Throttled connection, cold cache

CLS

0.040

Cumulative layout shift on load

SEO and GEO subscore

60.0

0 to 100, worth 12.37 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	80.4	pass
R01	P02	Authentication and session	11 Aug 2026 08:03 UTC	63.7	pass	Specification step wrote the tenancy rule down before any code depended on it. Schema correct on the first pass.
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:06 UTC	77.7	pass
R01	P04	Public REST API with keys	11 Aug 2026 08:09 UTC	62.1	pass
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:12 UTC	111.3	pass
R01	P06	Background jobs	11 Aug 2026 08:16 UTC	135.4	pass
R01	P07	Admin panel	11 Aug 2026 08:20 UTC	72.4	pass
R01	P08	Public marketing surface	11 Aug 2026 08:24 UTC	52.6	pass
R01	P09	Hardening pass	11 Aug 2026 08:26 UTC	88.8	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	58.8	pass
R02	P02	Authentication and session	12 Aug 2026 08:02 UTC	68.1	pass	Specification step wrote the tenancy rule down before any code depended on it. Schema correct on the first pass.
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:06 UTC	90.0	pass
R02	P04	Public REST API with keys	12 Aug 2026 08:09 UTC	109.5	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:13 UTC	143.7	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R02	P06	Background jobs	12 Aug 2026 08:17 UTC	132.9	pass
R02	P07	Admin panel	12 Aug 2026 08:22 UTC	48.7	pass
R02	P08	Public marketing surface	12 Aug 2026 08:24 UTC	64.4	pass
R02	P09	Hardening pass	12 Aug 2026 08:27 UTC	205.9	pass
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	49.7	partial	Validation added on the write path only. Read path left unguarded.
R03	P02	Authentication and session	13 Aug 2026 08:02 UTC	54.7	pass	Specification step wrote the tenancy rule down before any code depended on it. Schema correct on the first pass.
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:05 UTC	41.9	pass
R03	P04	Public REST API with keys	13 Aug 2026 08:08 UTC	93.0	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:11 UTC	144.6	pass
R03	P06	Background jobs	13 Aug 2026 08:16 UTC	197.4	pass
R03	P07	Admin panel	13 Aug 2026 08:21 UTC	66.1	pass
R03	P08	Public marketing surface	13 Aug 2026 08:24 UTC	45.3	pass
R03	P09	Hardening pass	13 Aug 2026 08:27 UTC	47.2	pass
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	54.8	pass
R04	P02	Authentication and session	14 Aug 2026 08:02 UTC	26.5	pass	Specification step wrote the tenancy rule down before any code depended on it. Schema correct on the first pass.
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:05 UTC	70.6	pass
R04	P04	Public REST API with keys	14 Aug 2026 08:08 UTC	67.9	pass
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:11 UTC	127.7	pass
R04	P06	Background jobs	14 Aug 2026 08:15 UTC	73.2	pass
R04	P07	Admin panel	14 Aug 2026 08:19 UTC	114.8	pass
R04	P08	Public marketing surface	14 Aug 2026 08:22 UTC	49.6	pass
R04	P09	Hardening pass	14 Aug 2026 08:25 UTC	80.8	pass
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	71.3	pass
R05	P02	Authentication and session	15 Aug 2026 08:03 UTC	56.8	pass	Specification step wrote the tenancy rule down before any code depended on it. Schema correct on the first pass.
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:06 UTC	79.0	pass
R05	P04	Public REST API with keys	15 Aug 2026 08:09 UTC	132.8	pass
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:13 UTC	79.0	fail	Agent looped on the same edit for the full timeout window of 20 minutes.
R05	P06	Background jobs	15 Aug 2026 08:16 UTC	254.4	pass
R05	P07	Admin panel	15 Aug 2026 08:23 UTC	61.4	pass
R05	P08	Public marketing surface	15 Aug 2026 08:26 UTC	57.7	pass
R05	P09	Hardening pass	15 Aug 2026 08:29 UTC	121.6	pass

Pricing

Free tier with a monthly interaction allowance. Paid plans from USD 20 per user per month.

Entry price: USD 20 / user / month
Priced from: vendor pricing page
Value subscore: 78.0
Index points per euro: 4.43

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: Your repository, any framework
deploy: Not included
database: Whatever you already run
auth: It wires the library you choose
background jobs: Planned in the spec, then implemented
webhooks: Signed, delivery log when asked
rest api: Written from the spec it produced
mcp server: Yes
export code: The code was never anywhere else
custom domain: Your hosting decides
ssr: Your framework decides

Screenshot

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

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

Kiro, 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
Kiro pricing page	https://kiro.dev/pricing	14 Aug 2026
Kiro product site	https://kiro.dev	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.

Kiro head to head

cursor vs kiro

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

78.01

Lab index

75.67

3 readers, 28 axis scores, last change 30 Aug 2026. Readers rate Kiro 2.3 points above 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	18.55%	84.0	85.7	3
Reliability	18.56%	93.3	93.3	3
Scalability	13.4%	80.0	81.3	3
SEO and GEO	12.37%	60.0	65.0	3
API and MCP	9.28%	72.0	76.0	3
Integrations	8.25%	74.0	75.7	3
Design output	7.22%	65.0	67.5	2
Turn latency score	7.22%	43.4	49.0	3
Value	5.15%	78.0	80.5	2

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

n/a

0 published open ratings, submitted without an account

Lab index

75.67

Measured, not voted

Gap to the measurement

n/a

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 42 times, partially 2 times and failed 1 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.