coding-agent / rank 14 of 41 / cycle 04
Factory benchmark
Built for teams rather than individuals, and the difference is visible in the operational prompts: it attached the change to a ticket, wrote a migration plan and produced a rollback path without being asked. It is slow and it is priced for organisations, so an individual will find better value elsewhere in this group. The API subscore is the second strongest in the agent group.
Composite index
71.52
of 100 | ▲ 1 versus cycle 03
At a glance
Composite index
71.52
rank 14 of 41
Rank
#14
of 41 measured builders
Median speed
161.7 s
p10 84.8 s, p90 350.8 s
Reliability
82.2%
strict pass rate
SEO score
56.0
0 to 100, SEO and GEO axis
Three strongest axes
- Code ownership93.0
- Reliability82.2
- Scalability82.0
Three weakest axes
- Speed19.4
- SEO and GEO56.0
- Design output62.0
Median per prompt
161.7 s
p10 84.8 s, p90 350.8 s
Strict pass rate
82.2%
37 pass, 5 partial, 3 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
EUR 36.00
Cheapest plan that can finish the specification
Per axis subscores
Composite recomputed from these ten rows: 71.52. That is the arithmetic behind the index, and you can repeat it by hand.
| Axis | Subscore 0 to 100, tick is the roster median | Score | Median | Weight % | Contribution |
|---|---|---|---|---|---|
| Agent performance | 81.0 | 75.0 | 18 | 14.58 | |
| Reliability | 82.2 | 71.1 | 18 | 14.80 | |
| Scalability | 82.0 | 70.0 | 13 | 10.66 | |
| SEO and GEO | 56.0 | 58.0 | 12 | 6.72 | |
| API and MCP | 76.0 | 62.0 | 9 | 6.84 | |
| Integrations | 78.0 | 66.0 | 8 | 6.24 | |
| Design output | 62.0 | 71.0 | 7 | 4.34 | |
| Speed | 19.4 | 33.0 | 7 | 1.36 | |
| Value | 64.0 | 76.0 | 5 | 3.20 | |
| Code ownership | 93.0 | 90.0 | 3 | 2.79 |
Speed distribution
Every recorded prompt duration for Factory, in seconds. The cyan tick on the whisker is the median.
Spread against the cohort
p10 84.8 s / median 161.7 s / p90 350.8 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 2.17x.
Outcome split
37 pass / 5 partial / 3 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
19.0 KB
19,456 bytes of real text content with scripts blocked
LCP
1,940 ms
Throttled connection, cold cache
CLS
0.050
Cumulative layout shift on load
SEO and GEO subscore
56.0
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.
| Run | Prompt | Prompt target | Started | Duration (s) | Outcome | Note |
|---|---|---|---|---|---|---|
| R01 | P01 | Tenant and user model | 11 Aug 2026 08:00 UTC | 102.7 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:03 UTC | 175.8 | pass | |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:08 UTC | 132.5 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:12 UTC | 204.5 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:18 UTC | 148.2 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:22 UTC | 184.0 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:27 UTC | 151.4 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:32 UTC | 155.1 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:36 UTC | 158.0 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 148.8 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:04 UTC | 97.7 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:08 UTC | 203.4 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:13 UTC | 401.5 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:22 UTC | 320.8 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:29 UTC | 345.5 | pass | |
| R02 | P07 | Admin panel | 12 Aug 2026 08:37 UTC | 116.9 | pass | |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:41 UTC | 74.0 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:44 UTC | 202.3 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 156.6 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:04 UTC | 336.6 | partial | Required one clarifying instruction before the criterion was met. |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:12 UTC | 116.3 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:16 UTC | 190.1 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:21 UTC | 266.7 | fail | Task abandoned by the agent with no artifact produced. |
| R03 | P06 | Background jobs | 13 Aug 2026 08:27 UTC | 145.7 | pass | |
| R03 | P07 | Admin panel | 13 Aug 2026 08:32 UTC | 344.2 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:39 UTC | 55.5 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:42 UTC | 43.9 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 390.1 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:08 UTC | 161.7 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:13 UTC | 76.2 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:16 UTC | 178.8 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:21 UTC | 492.8 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:31 UTC | 448.5 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:41 UTC | 292.2 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:48 UTC | 100.3 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:51 UTC | 161.7 | partial | Validation added on the write path only. Read path left unguarded. |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 207.7 | pass | |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:05 UTC | 69.3 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:08 UTC | 351.8 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:16 UTC | 349.4 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:24 UTC | 158.0 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:28 UTC | 146.2 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:33 UTC | 193.9 | partial | Required one clarifying instruction before the criterion was met. |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:38 UTC | 152.4 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:43 UTC | 230.3 | pass |
Pricing
From EUR 36 per seat per month. Enterprise plans are quoted rather than listed.
- Entry price
- EUR 36.00
- Value subscore
- 64.0
- Index points per euro
- 1.99
Capabilities as measured
- stack
- Your repository, any framework
- deploy
- Pipeline aware, it writes the pipeline change
- database
- Whatever you already run, migrations planned
- auth
- It wires the library you choose
- background jobs
- Durable queue by default
- webhooks
- Signed with a delivery log
- rest api
- Versioned and documented
- mcp server
- Yes
- export code
- The code was never anywhere else
- custom domain
- Your hosting decides
- ssr
- Your framework decides
Screenshot
Factory landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Factory, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Factory pricing page | https://factory.ai/pricing | 14 Aug 2026 |
| Factory product site | https://factory.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 3.6 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.
Factory 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
64.41
Lab index
71.52
4 readers, 35 axis scores, last change 15 Aug 2026. Readers rate Factory 7.1 points below the measurement.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 81.0 | 74.3 | 4 | |
| Reliability | 18% | 82.2 | 77.3 | 4 | |
| Scalability | 13% | 82.0 | 75.8 | 4 | |
| SEO and GEO | 12% | 56.0 | 49.0 | 4 | |
| API and MCP | 9% | 76.0 | 71.8 | 4 | |
| Integrations | 8% | 78.0 | 71.8 | 4 | |
| Design output | 7% | 62.0 | 49.0 | 1 | |
| Speed | 7% | 19.4 | 14.0 | 4 | |
| Value | 5% | 64.0 | 44.0 | 2 | |
| Code ownership | 3% | 93.0 | 86.8 | 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
71.52
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
Built for teams rather than individuals, and the difference is visible in the operational prompts: it attached the change to a ticket, wrote a migration plan and produced a rollback path without being asked. It is slow and it is priced for organisations, so an individual will find better value elsewhere in this group. The API subscore is the second strongest in the agent group.
Across 45 recorded executions this product met the published pass criterion cleanly 37 times, partially 5 times and failed 3 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.