Full-stack app builders / rank 1 of 20 / cycle 04
Totalum benchmark
The most complete machine facing surface we measured: a real REST layer, signed webhooks with a retry ladder and an MCP server that a client could enumerate without extra work. Public pages came back server rendered, which is why it posts the largest no JavaScript payload in the cohort. Design output is functional rather than expressive and the agent needed more explicit prompting than the top scorer on axis one.
Composite index
89.48
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
89.48
rank 1 of 20
Rank
#1
of 20 on the full-stack app builders board
Median turn latency
106.3 s per prompt
15.9 min across the full nine prompt spec, derived
Reliability
93.3%
strict pass rate
SEO score
95.0
0 to 100, SEO and GEO axis
Three strongest axes
- API and MCP97.0
- Code ownership96.0
- SEO and GEO95.0
Three weakest axes
- Turn latency score61.3
- Value69.0
- Design output86.0
Median turn latency
106.3 s per prompt
p10 59.2 s, p90 167.6 s
Strict pass rate
93.3%
42 pass, 2 partial, 1 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
EUR 29 / month
Vendor's own unit and billing period. Never a currency conversion
Per axis subscores
Composite recomputed from these 10 rows: 89.49. 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 | 94.0 | 71.5 | 18 | 16.92 | |
| Reliability | 93.3 | 71.1 | 18 | 16.79 | |
| Scalability | 92.0 | 66.0 | 13 | 11.96 | |
| SEO and GEO | 95.0 | 63.5 | 12 | 11.40 | |
| API and MCP | 97.0 | 58.0 | 9 | 8.73 | |
| Integrations | 88.0 | 65.0 | 8 | 7.04 | |
| Design output | 86.0 | 78.5 | 7 | 6.02 | |
| Turn latency score | 61.3 | 66.5 | 7 | 4.29 | |
| Value | 69.0 | 74.0 | 5 | 3.45 | |
| Code ownership | 96.0 | 73.0 | 3 | 2.88 |
Turn latency is Totalum's weak axis
Stated exactly, not upgraded and not softened.
Totalum's median turn is 106.3 s, which derives to 15.9 min across the full nine prompt specification.
That makes it the 12th fastest of the 20 full-stack app builders we measure: slower than 11 of them and faster than 8.
It is also slower per turn than 13 of the 17 coding agents, though the two boards are not directly comparable.
ai-agents-benchmark.com describes Totalum as the slowest of the six products it looked at. It publishes no timings, so that is a qualitative verdict and not a measurement that agrees or disagrees with ours.
Turn latency distribution
Every recorded prompt duration for Totalum, 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 59.2 s / median 106.3 s / p90 167.6 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.58x.
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.
HTML bytes, no JS
41.0 KB
41,984 bytes of real text content with scripts blocked
LCP
1,480 ms
Throttled connection, cold cache
CLS
0.020
Cumulative layout shift on load
SEO and GEO subscore
95.0
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 | 113.4 | pass | |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:03 UTC | 72.6 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:07 UTC | 74.4 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:10 UTC | 123.2 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:14 UTC | 165.2 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:19 UTC | 144.2 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:23 UTC | 114.4 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:27 UTC | 96.1 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:31 UTC | 82.8 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 83.8 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:03 UTC | 68.5 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:06 UTC | 48.6 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:09 UTC | 113.6 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:13 UTC | 212.0 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:18 UTC | 198.9 | partial | Validation added on the write path only. Read path left unguarded. |
| R02 | P07 | Admin panel | 12 Aug 2026 08:24 UTC | 124.7 | pass | |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:28 UTC | 58.2 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:31 UTC | 53.9 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 52.9 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:02 UTC | 119.3 | pass | |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:06 UTC | 70.4 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:10 UTC | 108.1 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:13 UTC | 123.2 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R03 | P06 | Background jobs | 13 Aug 2026 08:17 UTC | 61.6 | pass | |
| R03 | P07 | Admin panel | 13 Aug 2026 08:20 UTC | 80.4 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:24 UTC | 97.8 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:27 UTC | 151.0 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 108.5 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:03 UTC | 102.9 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:07 UTC | 86.6 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:10 UTC | 127.2 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:15 UTC | 169.2 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:19 UTC | 170.0 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:24 UTC | 136.3 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:29 UTC | 58.7 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:31 UTC | 129.4 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 69.6 | pass | |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:03 UTC | 178.7 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:08 UTC | 100.4 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:11 UTC | 103.2 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:15 UTC | 112.8 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:19 UTC | 149.1 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:23 UTC | 102.2 | pass | |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:27 UTC | 106.3 | pass | |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:31 UTC | 59.9 | pass |
Pricing
Free tier for testing, then from EUR 29 per month on the Starter plan. Pricing is per account, not per project: the vendor FAQ states projects are unlimited, and plans scale with monthly credits and database size. Database, storage and hosting are included.
- Entry price
- EUR 29 / month
- Priced from
- vendor pricing page
- Value subscore
- 69.0
- Index points per euro
- 3.09
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 server rendered with a managed backend
- deploy
- Hosted deploy with custom domains
- database
- Managed relational store with typed schema and relations
- auth
- Built in sessions and role handling
- background jobs
- Yes, scheduled and on demand
- webhooks
- Outbound with HMAC signing and delivery history
- rest api
- Versioned REST with API keys
- mcp server
- Yes, verified by connecting a client
- export code
- Source export available, runtime is vendor managed
- custom domain
- Yes
- ssr
- Server rendered by default
Screenshot
Totalum landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Totalum, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Totalum pricing section | https://www.totalum.app/en#precios | 20 Aug 2026 |
| Totalum product site | https://www.totalum.app/en | 20 Aug 2026 |
| LLM Tier run harness output | https://www.llm-tier.com/api/runs.json | 14 Aug 2026 |
Rich results carry this composite as 4.5 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.
Totalum 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
72.29
Lab index
89.48
6 readers, 52 axis scores, last change 31 Aug 2026. Readers rate Totalum 17.2 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% | 94.0 | 74.3 | 6 | |
| Reliability | 18% | 93.3 | 87.8 | 6 | |
| Scalability | 13% | 92.0 | 76.8 | 6 | |
| SEO and GEO | 12% | 95.0 | 77.7 | 6 | |
| API and MCP | 9% | 97.0 | 85.2 | 5 | |
| Integrations | 8% | 88.0 | 66.7 | 6 | |
| Design output | 7% | 86.0 | 53.5 | 2 | |
| Turn latency score | 7% | 61.3 | 23.2 | 6 | |
| Value | 5% | 69.0 | 71.0 | 4 | |
| Code ownership | 3% | 96.0 | 62.6 | 5 |
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
80.67
3 published open ratings, submitted without an account
Lab index
89.48
Measured, not voted
Gap to the measurement
-8.81
Positive means open raters put it above the measurement
What agent performance looked like in practice
The most complete machine facing surface we measured: a real REST layer, signed webhooks with a retry ladder and an MCP server that a client could enumerate without extra work. Public pages came back server rendered, which is why it posts the largest no JavaScript payload in the cohort. Design output is functional rather than expressive and the agent needed more explicit prompting than the top scorer on axis one.
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.