Full-stack app builders / rank 2 of 20 / cycle 04
Firebase Studio benchmarkSunsetting March 22, 2027
Lifecycle notice, August 22, 2026: Google is sunsetting Firebase Studio on March 22, 2027, after which new workspaces can no longer be created. Google's stated migration paths are Google AI Studio and Google Antigravity, which is measured separately on this board, and the guide is at https://firebase.google.com/docs/studio/migrating-project. Everything below was measured while the product is fully available and is not discounted for a date seven months out. The widest integration surface of any builder we measured: auth, storage, scheduled functions and a managed datastore all attach without leaving the workspace. It pays for that in wall clock, since every prompt round trips through a provisioned cloud workspace rather than a local sandbox. Public pages came back client rendered unless server rendering was asked for by name, which is what holds the SEO subscore down.
Composite index
80.92
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.
Lifecycle notice
Google is sunsetting Firebase Studio on March 22, 2027
After that date, new Firebase Studio workspaces can no longer be created, though workspaces already running are unaffected today. Google names Google AI Studio and Google Antigravity as the migration paths. Every score on this page was measured while Firebase Studio is fully available and carries no discount for the date ahead.
Verified August 22, 2026
At a glance
Composite index
80.92
rank 2 of 20
Rank
#2
of 20 on the full-stack app builders board
Median turn latency
100.3 s per prompt
15.0 min across the full nine prompt spec, derived
Reliability
86.7%
strict pass rate
SEO score
73.0
0 to 100, SEO and GEO axis
Three strongest axes
- Value92.0
- Integrations90.0
- Scalability87.0
Three weakest axes
- Turn latency score65.0
- Design output72.0
- SEO and GEO73.0
Median turn latency
100.3 s per prompt
p10 65.8 s, p90 161.3 s
Strict pass rate
86.7%
39 pass, 5 partial, 1 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
No cost
Vendor's own unit and billing period. Never a currency conversion
Per axis subscores
Composite recomputed from these 10 rows: 80.92. 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.
| Axis | Subscore 0 to 100, tick is the roster median | Score | Median | Weight % | Contribution |
|---|---|---|---|---|---|
| Agent performance | 79.0 | 71.5 | 18 | 14.22 | |
| Reliability | 86.7 | 71.1 | 18 | 15.61 | |
| Scalability | 87.0 | 66.0 | 13 | 11.31 | |
| SEO and GEO | 73.0 | 63.5 | 12 | 8.76 | |
| API and MCP | 79.0 | 58.0 | 9 | 7.11 | |
| Integrations | 90.0 | 65.0 | 8 | 7.20 | |
| Design output | 72.0 | 78.5 | 7 | 5.04 | |
| Turn latency score | 65.0 | 66.5 | 7 | 4.55 | |
| Value | 92.0 | 74.0 | 5 | 4.60 | |
| Code ownership | 84.0 | 73.0 | 3 | 2.52 |
Turn latency distribution
Every recorded prompt duration for Firebase Studio, in seconds. Median wall clock time for one prompt, not for a whole build. The cyan tick on the whisker is the median.
Spread against the cohort
p10 65.8 s / median 100.3 s / p90 161.3 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.61x.
Outcome split
39 pass / 5 partial / 1 fail
SEO and GEO measurements
Taken from the public marketing page this product generated in prompt 8, fetched with JavaScript disabled.
HTML bytes, no JS
22.0 KB
22,528 bytes of real text content with scripts blocked
LCP
1,980 ms
Throttled connection, cold cache
CLS
0.050
Cumulative layout shift on load
SEO and GEO subscore
73.0
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.
| Run | Prompt | Prompt target | Started | Duration (s) | Outcome | Note |
|---|---|---|---|---|---|---|
| R01 | P01 | Tenant and user model | 11 Aug 2026 08:00 UTC | 136.6 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:04 UTC | 121.0 | partial | Validation added on the write path only. Read path left unguarded. |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:08 UTC | 123.1 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:12 UTC | 50.9 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:15 UTC | 125.4 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:19 UTC | 73.2 | partial | Validation added on the write path only. Read path left unguarded. |
| R01 | P07 | Admin panel | 11 Aug 2026 08:22 UTC | 87.4 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:25 UTC | 59.6 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:28 UTC | 91.0 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 96.2 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:03 UTC | 130.7 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:07 UTC | 100.3 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:11 UTC | 119.5 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:15 UTC | 176.4 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:20 UTC | 89.3 | pass | |
| R02 | P07 | Admin panel | 12 Aug 2026 08:23 UTC | 95.1 | pass | |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:27 UTC | 179.5 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:32 UTC | 109.7 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 70.0 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:03 UTC | 69.0 | pass | |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:06 UTC | 73.9 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:09 UTC | 94.9 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:13 UTC | 103.4 | pass | |
| R03 | P06 | Background jobs | 13 Aug 2026 08:16 UTC | 284.9 | pass | |
| R03 | P07 | Admin panel | 13 Aug 2026 08:23 UTC | 117.4 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:27 UTC | 87.6 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:31 UTC | 117.1 | fail | Task abandoned by the agent with no artifact produced. |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 31.0 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:02 UTC | 64.5 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:05 UTC | 164.3 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:10 UTC | 133.7 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:14 UTC | 119.5 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:18 UTC | 114.6 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:22 UTC | 77.2 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:25 UTC | 67.8 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:28 UTC | 156.8 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 111.6 | partial | Required one clarifying instruction before the criterion was met. |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:03 UTC | 80.5 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:07 UTC | 100.4 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:10 UTC | 88.0 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:14 UTC | 96.8 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:17 UTC | 120.7 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:21 UTC | 71.6 | pass | |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:25 UTC | 63.6 | partial | Error envelope inconsistent between two of the endpoints. |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:28 UTC | 210.5 | pass |
Pricing
No seat price during preview. The generated project bills through the underlying cloud plan, so the running cost depends on usage rather than a licence.
- Entry price
- No cost
- Priced from
- vendor pricing page
- Value subscore
- 92.0
- Index points per euro
- No licence fee
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
- Framework of your choice inside a cloud workspace
- deploy
- Managed hosting with preview channels
- database
- Managed document store, relational engine on request
- auth
- First party auth with provider plugins
- background jobs
- Yes, scheduled and event triggered functions
- webhooks
- Outbound supported, signing written by hand
- rest api
- Generated per function, no key manager by default
- mcp server
- Yes
- export code
- Full source, standard project layout
- custom domain
- Yes
- ssr
- Client rendered unless requested
Screenshot
Firebase Studio landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Firebase Studio, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Firebase Studio sunset banner, vendor homepage | https://firebase.studio | 22 Aug 2026 |
| Google migration guide for Firebase Studio projects | https://firebase.google.com/docs/studio/migrating-project | 22 Aug 2026 |
| Firebase Studio pricing page | https://firebase.studio/pricing | 14 Aug 2026 |
| Firebase Studio product site | https://firebase.studio | 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.
Firebase Studio head to head
Reader index
Voted by readers with an account, one score per person per axis. Published beside the lab index, never inside it.
Reader index
74.74
Lab index
80.92
5 readers, 42 axis scores, last change 31 Aug 2026. Readers rate Firebase Studio 6.2 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.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 79.0 | 75.4 | 5 | |
| Reliability | 18% | 86.7 | 85.8 | 5 | |
| Scalability | 13% | 87.0 | 80.6 | 5 | |
| SEO and GEO | 12% | 73.0 | 68.4 | 5 | |
| API and MCP | 9% | 79.0 | 74.3 | 4 | |
| Integrations | 8% | 90.0 | 86.4 | 5 | |
| Design output | 7% | 72.0 | 73.0 | 1 | |
| Turn latency score | 7% | 65.0 | 28.8 | 5 | |
| Value | 5% | 92.0 | 78.3 | 3 | |
| Code ownership | 3% | 84.0 | 80.0 | 4 |
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
80.92
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
Lifecycle notice, August 22, 2026: Google is sunsetting Firebase Studio on March 22, 2027, after which new workspaces can no longer be created. Google's stated migration paths are Google AI Studio and Google Antigravity, which is measured separately on this board, and the guide is at https://firebase.google.com/docs/studio/migrating-project. Everything below was measured while the product is fully available and is not discounted for a date seven months out. The widest integration surface of any builder we measured: auth, storage, scheduled functions and a managed datastore all attach without leaving the workspace. It pays for that in wall clock, since every prompt round trips through a provisioned cloud workspace rather than a local sandbox. Public pages came back client rendered unless server rendering was asked for by name, which is what holds the SEO subscore down.
Across 45 recorded executions this product met the published pass criterion cleanly 39 times, partially 5 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.