How fast is Antigravity?

The median wall clock time is 78.7 seconds per prompt, with a tenth percentile of 45.0 seconds and a ninetieth percentile of 123.1 seconds across 45 recorded executions.

How reliable is Antigravity?

73.3% of recorded executions met the published pass criterion with no operator intervention. 7 were partial and 5 failed outright. Every one of those rows is published on this page.

Can I export the code from Antigravity?

The code was never anywhere else. The code ownership subscore is 96.0 out of 100.

coding-agent / rank 13 of 41 / cycle 04

Antigravity benchmark

Plans across several files at once and reports what it intends to do before doing it, which makes a failed run cheap to diagnose. It is the best value entry in the agent group at present because the licence costs nothing, and that will change. Prompt 6 was the weak point: durable work was queued correctly in three of five runs and left as a timer in the other two.

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

Composite index

71.91

of 100 | ▲ 1 versus cycle 03

At a glance

Composite index

71.91

rank 13 of 41

Rank

#13

of 41 measured builders

Median speed

78.7 s

p10 45.0 s, p90 123.1 s

Reliability

73.3%

strict pass rate

SEO score

58.0

0 to 100, SEO and GEO axis

Three strongest axes

Code ownership96.0
Value86.0
Agent performance83.0

Three weakest axes

Speed39.9
SEO and GEO58.0
Design output70.0

Median per prompt

78.7 s

p10 45.0 s, p90 123.1 s

Strict pass rate

73.3%

33 pass, 7 partial, 5 fail

Executions recorded

5 runs of 9 prompts

Entry price

EUR 0.00

Cheapest plan that can finish the specification

Per axis subscores

Composite recomputed from these ten rows: 71.91. 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	83.0	75.0	18	14.94
Reliability	73.3	71.1	18	13.19
Scalability	76.0	70.0	13	9.88
SEO and GEO	58.0	58.0	12	6.96
API and MCP	70.0	62.0	9	6.30
Integrations	72.0	66.0	8	5.76
Design output	70.0	71.0	7	4.90
Speed	39.9	33.0	7	2.79
Value	86.0	76.0	5	4.30
Code ownership	96.0	90.0	3	2.88

Speed distribution

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

min 25.6 smax 189.2 s

Spread against the cohort

p10 45.0 s / median 78.7 s / p90 123.1 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.56x.

Outcome split

33 pass / 7 partial / 5 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

1,820 ms

Throttled connection, cold cache

CLS

0.040

Cumulative layout shift on load

SEO and GEO subscore

58.0

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	61.3	fail	Deployed URL returned 500 on every request.
R01	P02	Authentication and session	11 Aug 2026 08:03 UTC	25.6	pass
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:05 UTC	136.8	pass
R01	P04	Public REST API with keys	11 Aug 2026 08:09 UTC	64.1	fail	Deployed URL returned 500 on every request.
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:12 UTC	99.5	pass
R01	P06	Background jobs	11 Aug 2026 08:16 UTC	90.6	pass
R01	P07	Admin panel	11 Aug 2026 08:19 UTC	110.9	fail	Task abandoned by the agent with no artifact produced.
R01	P08	Public marketing surface	11 Aug 2026 08:23 UTC	84.1	fail	Task abandoned by the agent with no artifact produced.
R01	P09	Hardening pass	11 Aug 2026 08:27 UTC	30.5	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	120.5	pass
R02	P02	Authentication and session	12 Aug 2026 08:04 UTC	66.1	pass
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:07 UTC	78.7	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R02	P04	Public REST API with keys	12 Aug 2026 08:10 UTC	189.2	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:15 UTC	129.9	pass
R02	P06	Background jobs	12 Aug 2026 08:19 UTC	100.8	pass
R02	P07	Admin panel	12 Aug 2026 08:23 UTC	43.9	pass
R02	P08	Public marketing surface	12 Aug 2026 08:26 UTC	46.6	pass
R02	P09	Hardening pass	12 Aug 2026 08:28 UTC	124.9	pass
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	68.8	pass
R03	P02	Authentication and session	13 Aug 2026 08:03 UTC	86.9	pass
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:06 UTC	104.2	partial	Error envelope inconsistent between two of the endpoints.
R03	P04	Public REST API with keys	13 Aug 2026 08:10 UTC	88.6	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:13 UTC	149.6	pass
R03	P06	Background jobs	13 Aug 2026 08:18 UTC	75.8	partial	Durable work left as a timer rather than a queue. Scheduled work did not survive a redeploy.
R03	P07	Admin panel	13 Aug 2026 08:21 UTC	87.9	pass
R03	P08	Public marketing surface	13 Aug 2026 08:25 UTC	60.4	pass
R03	P09	Hardening pass	13 Aug 2026 08:28 UTC	54.1	pass
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	115.9	pass
R04	P02	Authentication and session	14 Aug 2026 08:03 UTC	69.4	partial	Required one clarifying instruction before the criterion was met.
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:07 UTC	61.0	pass
R04	P04	Public REST API with keys	14 Aug 2026 08:10 UTC	101.3	pass
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:13 UTC	90.3	pass
R04	P06	Background jobs	14 Aug 2026 08:17 UTC	120.2	pass
R04	P07	Admin panel	14 Aug 2026 08:21 UTC	111.4	pass
R04	P08	Public marketing surface	14 Aug 2026 08:25 UTC	85.4	pass
R04	P09	Hardening pass	14 Aug 2026 08:28 UTC	46.7	partial	Error envelope inconsistent between two of the endpoints.
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	28.9	pass
R05	P02	Authentication and session	15 Aug 2026 08:02 UTC	73.9	fail	Agent looped on the same edit for the full timeout window of 20 minutes.
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:05 UTC	60.9	pass
R05	P04	Public REST API with keys	15 Aug 2026 08:08 UTC	66.3	pass
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:11 UTC	70.3	pass
R05	P06	Background jobs	15 Aug 2026 08:15 UTC	77.9	partial	Durable work left as a timer rather than a queue. Scheduled work did not survive a redeploy.
R05	P07	Admin panel	15 Aug 2026 08:18 UTC	73.2	partial	Validation added on the write path only. Read path left unguarded.
R05	P08	Public marketing surface	15 Aug 2026 08:21 UTC	79.2	pass
R05	P09	Hardening pass	15 Aug 2026 08:24 UTC	43.9	pass

Pricing

Free while in preview, with rate limits rather than a price. Model usage is metered above the allowance.

Entry price: EUR 0.00
Value subscore: 86.0
Index points per euro: 71.91

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: Mixed, queue in most runs
webhooks: Signed when the criterion names it
rest api: Written to your conventions
mcp server: Yes
export code: The code was never anywhere else
custom domain: Your hosting decides
ssr: Your framework decides

Screenshot

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

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

Antigravity, 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
Antigravity pricing page	https://antigravity.google/pricing	14 Aug 2026
Antigravity product site	https://antigravity.google	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 3.6 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.

Antigravity head to head

antigravity vs jules

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

71.91

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
Axis	Weight	Lab	Readers	Votes
Agent performance	18%	83.0	87.0	1
Reliability	18%	73.3	75.0	1
Scalability	13%	76.0	85.0	1
SEO and GEO	12%	58.0	58.0	1
API and MCP	9%	70.0	75.0	1
Integrations	8%	72.0	71.0	1
Design output	7%	70.0	81.0	1
Speed	7%	39.9	48.0	1
Value	5%	86.0	92.0	1
Code ownership	3%	96.0	95.0	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

n/a

0 published open ratings, submitted without an account

Lab index

71.91

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 33 times, partially 7 times and failed 5 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.