Convex Chef logo

fullstack-builder / rank 17 of 41 / cycle 04

Convex Chef benchmark

The reactive backend underneath it does most of the work the operational prompts ask for, so scheduled functions, durable actions and consistent reads arrived without prompting. That is why it posts one of the best API subscores in the cohort despite a middling agent score. Where it struggles is anything conventionally relational: prompt 2 needed rework in three of five runs to express the tenancy constraint the way the platform prefers.

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

Composite index

70.50

of 100 | 1 versus cycle 03

At a glance

Composite index

70.50

rank 17 of 41

Rank

#17

of 41 measured builders

Median speed

88.7 s

p10 51.5 s, p90 142.4 s

Reliability

60.0%

strict pass rate

SEO score

65.0

0 to 100, SEO and GEO axis

Three strongest axes

  • Code ownership88.0
  • Scalability84.0
  • API and MCP82.0

Three weakest axes

  • Speed35.4
  • Reliability60.0
  • SEO and GEO65.0

Median per prompt

88.7 s

p10 51.5 s, p90 142.4 s

Strict pass rate

60.0%

27 pass, 8 partial, 10 fail

Executions recorded

45

5 runs of 9 prompts

Entry price

EUR 25.00

Cheapest plan that can finish the specification

Per axis subscores

Composite recomputed from these ten rows: 70.50. That is the arithmetic behind the index, and you can repeat it by hand.

Per axis subscores against the roster median, and weighted contribution
AxisSubscore 0 to 100, tick is the roster medianScoreMedianWeight %Contribution
Agent performance75.075.01813.50
Reliability60.071.11810.80
Scalability84.070.01310.92
SEO and GEO65.058.0127.80
API and MCP82.062.097.38
Integrations72.066.085.76
Design output76.071.075.32
Speed35.433.072.48
Value78.076.053.90
Code ownership88.090.032.64

Speed distribution

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

min 45.2 smax 312.2 s

Spread against the cohort

p10 51.5 s / median 88.7 s / p90 142.4 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

27 pass / 8 partial / 10 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

12.0 KB

12,288 bytes of real text content with scripts blocked

LCP

1,840 ms

Throttled connection, cold cache

CLS

0.040

Cumulative layout shift on load

SEO and GEO subscore

65.0

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.

Raw per run measurements
RunPromptPrompt targetStartedDuration (s)OutcomeNote
R01P01Tenant and user model11 Aug 2026 08:00 UTC49.1partialError envelope inconsistent between two of the endpoints.
R01P02Authentication and session11 Aug 2026 08:02 UTC77.8partialValidation added on the write path only. Read path left unguarded.
R01P03Projects CRUD with tenancy11 Aug 2026 08:06 UTC70.6pass
R01P04Public REST API with keys11 Aug 2026 08:09 UTC132.7pass
R01P05Outbound webhooks with signatures11 Aug 2026 08:13 UTC103.5pass
R01P06Background jobs11 Aug 2026 08:17 UTC115.4pass
R01P07Admin panel11 Aug 2026 08:21 UTC59.9failAgent looped on the same edit for the full timeout window of 20 minutes.
R01P08Public marketing surface11 Aug 2026 08:24 UTC99.4partialError envelope inconsistent between two of the endpoints.
R01P09Hardening pass11 Aug 2026 08:27 UTC141.2failBuild did not start after deploy. Recorded as a fail with the log preserved.
R02P01Tenant and user model12 Aug 2026 08:00 UTC93.5failAgent looped on the same edit for the full timeout window of 20 minutes.
R02P02Authentication and session12 Aug 2026 08:03 UTC73.9pass
R02P03Projects CRUD with tenancy12 Aug 2026 08:06 UTC67.3pass
R02P04Public REST API with keys12 Aug 2026 08:09 UTC127.6pass
R02P05Outbound webhooks with signatures12 Aug 2026 08:14 UTC65.6failTask abandoned by the agent with no artifact produced.
R02P06Background jobs12 Aug 2026 08:17 UTC312.2failAgent looped on the same edit for the full timeout window of 20 minutes.
R02P07Admin panel12 Aug 2026 08:24 UTC141.4pass
R02P08Public marketing surface12 Aug 2026 08:28 UTC51.5pass
R02P09Hardening pass12 Aug 2026 08:31 UTC88.1pass
R03P01Tenant and user model13 Aug 2026 08:00 UTC69.8pass
R03P02Authentication and session13 Aug 2026 08:03 UTC110.6partialDelivered the main path, missed the boundary case named in the pass criteria.
R03P03Projects CRUD with tenancy13 Aug 2026 08:07 UTC103.5pass
R03P04Public REST API with keys13 Aug 2026 08:10 UTC85.7failAgent looped on the same edit for the full timeout window of 20 minutes.
R03P05Outbound webhooks with signatures13 Aug 2026 08:14 UTC80.6pass
R03P06Background jobs13 Aug 2026 08:17 UTC143.1pass
R03P07Admin panel13 Aug 2026 08:21 UTC85.2pass
R03P08Public marketing surface13 Aug 2026 08:25 UTC51.5pass
R03P09Hardening pass13 Aug 2026 08:28 UTC114.5pass
R04P01Tenant and user model14 Aug 2026 08:00 UTC48.7pass
R04P02Authentication and session14 Aug 2026 08:02 UTC55.2partialError envelope inconsistent between two of the endpoints.
R04P03Projects CRUD with tenancy14 Aug 2026 08:05 UTC168.3pass
R04P04Public REST API with keys14 Aug 2026 08:10 UTC49.0partialDelivered the main path, missed the boundary case named in the pass criteria.
R04P05Outbound webhooks with signatures14 Aug 2026 08:13 UTC90.0failTask abandoned by the agent with no artifact produced.
R04P06Background jobs14 Aug 2026 08:16 UTC134.8pass
R04P07Admin panel14 Aug 2026 08:21 UTC100.5pass
R04P08Public marketing surface14 Aug 2026 08:24 UTC88.7pass
R04P09Hardening pass14 Aug 2026 08:28 UTC85.4pass
R05P01Tenant and user model15 Aug 2026 08:00 UTC56.1pass
R05P02Authentication and session15 Aug 2026 08:02 UTC115.5failAgent looped on the same edit for the full timeout window of 20 minutes.
R05P03Projects CRUD with tenancy15 Aug 2026 08:06 UTC73.8failAgent looped on the same edit for the full timeout window of 20 minutes.
R05P04Public REST API with keys15 Aug 2026 08:10 UTC152.4partialError envelope inconsistent between two of the endpoints.
R05P05Outbound webhooks with signatures15 Aug 2026 08:14 UTC179.4pass
R05P06Background jobs15 Aug 2026 08:19 UTC100.7pass
R05P07Admin panel15 Aug 2026 08:23 UTC83.2partialDelivered the main path, missed the boundary case named in the pass criteria.
R05P08Public marketing surface15 Aug 2026 08:26 UTC105.1failGenerated migration conflicted with the existing schema and was not reconciled.
R05P09Hardening pass15 Aug 2026 08:30 UTC45.2pass

Pricing

Free tier with generous limits. Paid plans from EUR 25 per month based on function calls and storage.

Entry price
EUR 25.00
Value subscore
78.0
Index points per euro
2.82

Capabilities as measured

stack
React with a reactive TypeScript backend
deploy
Hosted deploy
database
Reactive document store with transactions
auth
Built in with provider plugins
background jobs
Yes, durable scheduled functions
webhooks
Outbound with retries
rest api
HTTP actions with key handling
mcp server
Yes
export code
Full source export
custom domain
Yes
ssr
Supported

Screenshot

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

Convex Chef landing page, captured by the lab at 1440 by 900

Convex Chef, captured 14 Aug 2026.

Sources and fetch dates

Every claim on this page traces to one of these.

Sources with fetch dates
SourceURLFetched
Convex Chef pricing pagehttps://convex.dev/pricing14 Aug 2026
Convex Chef product sitehttps://convex.dev14 Aug 2026
LLM Tier run harness outputhttps://www.llm-tier.com/api/runs.json14 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.

Convex Chef 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

70.80

Lab index

70.50

3 readers, 26 axis scores, last change 13 Aug 2026. Readers rate Convex Chef 0.3 points above the measurement.

Reader mean against the measured lab subscore for each axis
AxisWeightLabReadersVotesReader mean
Agent performance18%75.077.73
Reliability18%60.056.73
Scalability13%84.085.33
SEO and GEO12%65.066.73
API and MCP9%82.082.03
Integrations8%72.072.33
Speed7%35.437.73
Value5%78.079.02
Code ownership3%88.094.03

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

70.50

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

The reactive backend underneath it does most of the work the operational prompts ask for, so scheduled functions, durable actions and consistent reads arrived without prompting. That is why it posts one of the best API subscores in the cohort despite a middling agent score. Where it struggles is anything conventionally relational: prompt 2 needed rework in three of five runs to express the tenancy constraint the way the platform prefers.

Across 45 recorded executions this product met the published pass criterion cleanly 27 times, partially 8 times and failed 10 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.