How fast is Claude Code?

The median wall clock time is 65.5 seconds per prompt, with a tenth percentile of 39.9 seconds and a ninetieth percentile of 100.7 seconds across 45 recorded executions.

How reliable is Claude Code?

91.1% of recorded executions met the published pass criterion with no operator intervention. 3 were partial and 1 failed outright. Every one of those rows is published on this page.

Can I export the code from Claude Code?

The code was never anywhere else. The code ownership subscore is 99.0 out of 100.

coding-agent / rank 2 of 41 / cycle 04

Claude Code benchmark

The highest strict pass rate in the agent group, and third highest in the whole index. It was the only agent that produced a signed webhook with a retry ladder in prompt 5 in all five runs without the criterion being restated, and the only one that added an idempotency key to the write path unprompted. It is a terminal agent with no interface of its own, so design and SEO reflect the stack it was pointed at rather than anything it invented.

Last run: 14 Aug 2026 17:40 UTCNext scheduled run: 21 Aug 2026 09:00 UTCOfficial site Claude Code reviews and ratings

Composite index

80.30

of 100 | ▼ 1 versus cycle 03

At a glance

Composite index

80.30

rank 2 of 41

Rank

of 41 measured builders

Median speed

65.5 s

p10 39.9 s, p90 100.7 s

Reliability

91.1%

strict pass rate

SEO score

62.0

0 to 100, SEO and GEO axis

Three strongest axes

Code ownership99.0
Agent performance95.0
Reliability91.1

Three weakest axes

Speed47.9
SEO and GEO62.0
Design output68.0

Median per prompt

65.5 s

p10 39.9 s, p90 100.7 s

Strict pass rate

91.1%

41 pass, 3 partial, 1 fail

Executions recorded

5 runs of 9 prompts

Entry price

EUR 17.00

Cheapest plan that can finish the specification

Per axis subscores

Composite recomputed from these ten rows: 80.30. That is the arithmetic behind the index, and you can repeat it by hand.

Weight table

Per axis subscores against the roster median, and weighted contribution
Axis	Score	Median	Weight %	Contribution
Agent performance	95.0	75.0	18	17.10
Reliability	91.1	71.1	18	16.40
Scalability	86.0	70.0	13	11.18
SEO and GEO	62.0	58.0	12	7.44
API and MCP	78.0	62.0	9	7.02
Integrations	76.0	66.0	8	6.08
Design output	68.0	71.0	7	4.76
Speed	47.9	33.0	7	3.35
Value	80.0	76.0	5	4.00
Code ownership	99.0	90.0	3	2.97

Speed distribution

Every recorded prompt duration for Claude Code, in seconds. The cyan tick on the whisker is the median.

min 21.8 smax 176.3 s

Spread against the cohort

p10 39.9 s / median 65.5 s / p90 100.7 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.54x.

Outcome split

41 pass / 3 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

26.0 KB

26,624 bytes of real text content with scripts blocked

LCP

1,680 ms

Throttled connection, cold cache

CLS

0.030

Cumulative layout shift on load

SEO and GEO subscore

62.0

0 to 100, worth 12 index points

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	46.6	pass
R01	P02	Authentication and session	11 Aug 2026 08:02 UTC	23.3	fail	Deployed URL returned 500 on every request.
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:05 UTC	87.2	pass
R01	P04	Public REST API with keys	11 Aug 2026 08:08 UTC	68.5	pass
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:11 UTC	70.0	pass	Signed payload with a retry ladder and a delivery log on the first attempt, criterion met without a follow up.
R01	P06	Background jobs	11 Aug 2026 08:14 UTC	57.8	pass
R01	P07	Admin panel	11 Aug 2026 08:17 UTC	103.3	pass
R01	P08	Public marketing surface	11 Aug 2026 08:21 UTC	68.0	pass
R01	P09	Hardening pass	11 Aug 2026 08:24 UTC	72.7	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	36.0	partial	Validation added on the write path only. Read path left unguarded.
R02	P02	Authentication and session	12 Aug 2026 08:02 UTC	89.9	pass
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:06 UTC	93.1	pass
R02	P04	Public REST API with keys	12 Aug 2026 08:09 UTC	111.0	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:13 UTC	98.2	pass	Signed payload with a retry ladder and a delivery log on the first attempt, criterion met without a follow up.
R02	P06	Background jobs	12 Aug 2026 08:17 UTC	75.9	pass
R02	P07	Admin panel	12 Aug 2026 08:20 UTC	50.4	pass
R02	P08	Public marketing surface	12 Aug 2026 08:23 UTC	32.7	pass
R02	P09	Hardening pass	12 Aug 2026 08:25 UTC	58.4	pass
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	47.5	pass
R03	P02	Authentication and session	13 Aug 2026 08:02 UTC	52.9	pass
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:05 UTC	65.6	pass
R03	P04	Public REST API with keys	13 Aug 2026 08:08 UTC	102.4	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:12 UTC	76.6	pass	Signed payload with a retry ladder and a delivery log on the first attempt, criterion met without a follow up.
R03	P06	Background jobs	13 Aug 2026 08:15 UTC	61.0	pass
R03	P07	Admin panel	13 Aug 2026 08:18 UTC	53.9	pass
R03	P08	Public marketing surface	13 Aug 2026 08:21 UTC	40.7	pass
R03	P09	Hardening pass	13 Aug 2026 08:24 UTC	53.5	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	59.5	pass
R04	P02	Authentication and session	14 Aug 2026 08:02 UTC	55.5	pass
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:05 UTC	74.8	partial	Pagination off by one at the final page boundary.
R04	P04	Public REST API with keys	14 Aug 2026 08:09 UTC	76.8	pass
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:12 UTC	176.3	pass	Signed payload with a retry ladder and a delivery log on the first attempt, criterion met without a follow up.
R04	P06	Background jobs	14 Aug 2026 08:17 UTC	43.2	pass
R04	P07	Admin panel	14 Aug 2026 08:20 UTC	90.6	pass
R04	P08	Public marketing surface	14 Aug 2026 08:23 UTC	76.0	pass
R04	P09	Hardening pass	14 Aug 2026 08:26 UTC	65.0	pass
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	21.8	pass
R05	P02	Authentication and session	15 Aug 2026 08:02 UTC	95.5	pass
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:05 UTC	65.5	pass
R05	P04	Public REST API with keys	15 Aug 2026 08:09 UTC	58.3	pass
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:12 UTC	88.4	pass	Signed payload with a retry ladder and a delivery log on the first attempt, criterion met without a follow up.
R05	P06	Background jobs	15 Aug 2026 08:15 UTC	105.0	pass
R05	P07	Admin panel	15 Aug 2026 08:19 UTC	48.6	pass
R05	P08	Public marketing surface	15 Aug 2026 08:22 UTC	39.3	pass
R05	P09	Hardening pass	15 Aug 2026 08:24 UTC	46.7	pass

Pricing

Included with a consumer subscription from EUR 17 per month, or metered per token through the API.

Entry price: EUR 17.00
Value subscore: 80.0
Index points per euro: 4.72

Capabilities as measured

stack: Your repository, any framework
deploy: Not included, it writes and runs the deploy steps
database: Whatever you already run
auth: It wires the library you choose
background jobs: Real queue when the criterion asks for durability
webhooks: Signed with a retry ladder by default
rest api: Versioned when asked, documented as it goes
mcp server: Yes, client and server
export code: The code was never anywhere else
custom domain: Your hosting decides
ssr: Your framework decides

Screenshot

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

Claude Code landing page, captured by the lab at 1440 by 900

Claude Code, 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
Claude Code pricing page	https://claude.com/pricing	14 Aug 2026
Claude Code product site	https://claude.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 4.0 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.

Claude Code head to head

cursor vs claude-code claude-code vs amp

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

85.23

Lab index

80.30

6 readers, 57 axis scores, last change 13 Aug 2026. Readers rate Claude Code 4.9 points above the measurement.

Reader mean against the measured lab subscore for each axis
Axis	Weight	Lab	Readers	Votes
Agent performance	18%	95.0	99.7	6
Reliability	18%	91.1	98.7	6
Scalability	13%	86.0	91.0	6
SEO and GEO	12%	62.0	64.4	5
API and MCP	9%	78.0	85.2	6
Integrations	8%	76.0	80.5	6
Design output	7%	68.0	72.5	4
Speed	7%	47.9	52.7	6
Value	5%	80.0	82.3	6
Code ownership	3%	99.0	99.7	6

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

80.30

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 41 times, partially 3 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.