Full-stack app builders / rank 9 of 20 / cycle 04
Softgen benchmark
Works best when it is given the whole specification at once rather than one prompt at a time, which is the opposite of how the vibeOps set is run, and the run to run variance shows it. Tenancy in prompt 3 was correct in every run, which several faster products cannot claim. The machine facing prompts are where it stops: no key management appeared without being asked twice.
Composite index
69.48
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
69.48
rank 9 of 20
Rank
#9
of 20 on the full-stack app builders board
Median turn latency
108.4 s per prompt
16.3 min across the full nine prompt spec, derived
Reliability
73.3%
strict pass rate
SEO score
66.0
0 to 100, SEO and GEO axis
Three strongest axes
- Design output78.0
- Agent performance74.0
- Code ownership74.0
Three weakest axes
- API and MCP58.0
- Turn latency score60.1
- SEO and GEO66.0
Median turn latency
108.4 s per prompt
p10 65.1 s, p90 176.3 s
Strict pass rate
73.3%
33 pass, 7 partial, 5 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
USD 25 / month
Vendor's own unit and billing period. Never a currency conversion
Per axis subscores
Composite recomputed from these 10 rows: 69.48. 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 | 74.0 | 71.5 | 18 | 13.32 | |
| Reliability | 73.3 | 71.1 | 18 | 13.19 | |
| Scalability | 68.0 | 66.0 | 13 | 8.84 | |
| SEO and GEO | 66.0 | 63.5 | 12 | 7.92 | |
| API and MCP | 58.0 | 58.0 | 9 | 5.22 | |
| Integrations | 70.0 | 65.0 | 8 | 5.60 | |
| Design output | 78.0 | 78.5 | 7 | 5.46 | |
| Turn latency score | 60.1 | 66.5 | 7 | 4.21 | |
| Value | 70.0 | 74.0 | 5 | 3.50 | |
| Code ownership | 74.0 | 73.0 | 3 | 2.22 |
Turn latency distribution
Every recorded prompt duration for Softgen, 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 65.1 s / median 108.4 s / p90 176.3 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.63x.
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.
HTML bytes, no JS
17.0 KB
17,408 bytes of real text content with scripts blocked
LCP
2,180 ms
Throttled connection, cold cache
CLS
0.060
Cumulative layout shift on load
SEO and GEO subscore
66.0
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 | 125.2 | pass | |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:04 UTC | 80.6 | pass | |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:07 UTC | 137.2 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:11 UTC | 145.4 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:16 UTC | 122.8 | fail | Deployed URL returned 500 on every request. |
| R01 | P06 | Background jobs | 11 Aug 2026 08:20 UTC | 98.4 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:23 UTC | 72.3 | partial | Error envelope inconsistent between two of the endpoints. |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:27 UTC | 99.1 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:30 UTC | 66.4 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 161.9 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:04 UTC | 266.0 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:11 UTC | 55.7 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:14 UTC | 140.7 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:18 UTC | 277.4 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:25 UTC | 108.0 | partial | Error envelope inconsistent between two of the endpoints. |
| R02 | P07 | Admin panel | 12 Aug 2026 08:28 UTC | 108.4 | pass | |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:32 UTC | 64.2 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:35 UTC | 94.7 | partial | Validation added on the write path only. Read path left unguarded. |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 91.1 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:03 UTC | 141.6 | pass | |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:07 UTC | 89.5 | partial | Error envelope inconsistent between two of the endpoints. |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:11 UTC | 167.0 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:16 UTC | 180.0 | pass | |
| R03 | P06 | Background jobs | 13 Aug 2026 08:21 UTC | 174.0 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R03 | P07 | Admin panel | 13 Aug 2026 08:26 UTC | 130.6 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:30 UTC | 97.9 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:33 UTC | 104.5 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 81.4 | partial | Validation added on the write path only. Read path left unguarded. |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:03 UTC | 155.6 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:07 UTC | 109.7 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:11 UTC | 177.8 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:16 UTC | 84.7 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:20 UTC | 411.6 | fail | Deployed URL returned 500 on every request. |
| R04 | P07 | Admin panel | 14 Aug 2026 08:29 UTC | 166.7 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:33 UTC | 47.6 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:36 UTC | 106.4 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 104.8 | pass | |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:03 UTC | 93.5 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:07 UTC | 122.1 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:11 UTC | 71.0 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:14 UTC | 62.6 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:17 UTC | 110.3 | partial | Pagination off by one at the final page boundary. |
| R05 | P07 | Admin panel | 15 Aug 2026 08:21 UTC | 110.8 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:25 UTC | 62.6 | pass | |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:28 UTC | 135.4 | pass |
Pricing
Free trial credits, then from USD 25 per month with a monthly message allowance.
Pricing note
Softgen publishes its plan prices with a bare dollar sign and no currency word anywhere on the page. USD is inferred by this lab rather than stated by the vendor, and the converted euro figure rests on that inference.
- Entry price
- USD 25 / month
- Priced from
- vendor pricing page
- Value subscore
- 70.0
- Index points per euro
- 3.25
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
- Next.js with a hosted backend
- deploy
- Hosted deploy
- database
- Managed Postgres
- auth
- Built in email and OAuth
- background jobs
- Partial, scheduled only
- webhooks
- Outbound, unsigned by default
- rest api
- Route handlers, keys added on request
- mcp server
- No
- export code
- Source export on paid plans
- custom domain
- Yes
- ssr
- Server rendered by default
Screenshot
Softgen landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Softgen, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Softgen pricing page | https://softgen.ai/pricing | 14 Aug 2026 |
| Softgen product site | https://softgen.ai | 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 3.5 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.
Reader index
Voted by readers with an account, one score per person per axis. Published beside the lab index, never inside it.
Reader index
not rated yet
Lab index
69.48
1 readers have scored 87% of the index weight so far. A reader index is published at 3 voters and 50% coverage.
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% | 74.0 | 74.0 | 1 | |
| Reliability | 18% | 73.3 | 73.0 | 1 | |
| SEO and GEO | 12% | 66.0 | 62.0 | 1 | |
| API and MCP | 9% | 58.0 | 65.0 | 1 | |
| Integrations | 8% | 70.0 | 79.0 | 1 | |
| Design output | 7% | 78.0 | 86.0 | 1 | |
| Turn latency score | 7% | 60.1 | 25.0 | 1 | |
| Value | 5% | 70.0 | 71.0 | 1 | |
| Code ownership | 3% | 74.0 | 71.0 | 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
69.48
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
Works best when it is given the whole specification at once rather than one prompt at a time, which is the opposite of how the vibeOps set is run, and the run to run variance shows it. Tenancy in prompt 3 was correct in every run, which several faster products cannot claim. The machine facing prompts are where it stops: no key management appeared without being asked twice.
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.