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.
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.
| Axis | Subscore 0 to 100, tick is the roster median | Score | Median | Weight % | Contribution |
|---|---|---|---|---|---|
| Agent performance | 75.0 | 75.0 | 18 | 13.50 | |
| Reliability | 60.0 | 71.1 | 18 | 10.80 | |
| Scalability | 84.0 | 70.0 | 13 | 10.92 | |
| SEO and GEO | 65.0 | 58.0 | 12 | 7.80 | |
| API and MCP | 82.0 | 62.0 | 9 | 7.38 | |
| Integrations | 72.0 | 66.0 | 8 | 5.76 | |
| Design output | 76.0 | 71.0 | 7 | 5.32 | |
| Speed | 35.4 | 33.0 | 7 | 2.48 | |
| Value | 78.0 | 76.0 | 5 | 3.90 | |
| Code ownership | 88.0 | 90.0 | 3 | 2.64 |
Speed distribution
Every recorded prompt duration for Convex Chef, in seconds. The cyan tick on the whisker is the median.
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.
| Run | Prompt | Prompt target | Started | Duration (s) | Outcome | Note |
|---|---|---|---|---|---|---|
| R01 | P01 | Tenant and user model | 11 Aug 2026 08:00 UTC | 49.1 | partial | Error envelope inconsistent between two of the endpoints. |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:02 UTC | 77.8 | partial | Validation added on the write path only. Read path left unguarded. |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:06 UTC | 70.6 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:09 UTC | 132.7 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:13 UTC | 103.5 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:17 UTC | 115.4 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:21 UTC | 59.9 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:24 UTC | 99.4 | partial | Error envelope inconsistent between two of the endpoints. |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:27 UTC | 141.2 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 93.5 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:03 UTC | 73.9 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:06 UTC | 67.3 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:09 UTC | 127.6 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:14 UTC | 65.6 | fail | Task abandoned by the agent with no artifact produced. |
| R02 | P06 | Background jobs | 12 Aug 2026 08:17 UTC | 312.2 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R02 | P07 | Admin panel | 12 Aug 2026 08:24 UTC | 141.4 | pass | |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:28 UTC | 51.5 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:31 UTC | 88.1 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 69.8 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:03 UTC | 110.6 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:07 UTC | 103.5 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:10 UTC | 85.7 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:14 UTC | 80.6 | pass | |
| R03 | P06 | Background jobs | 13 Aug 2026 08:17 UTC | 143.1 | pass | |
| R03 | P07 | Admin panel | 13 Aug 2026 08:21 UTC | 85.2 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:25 UTC | 51.5 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:28 UTC | 114.5 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 48.7 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:02 UTC | 55.2 | partial | Error envelope inconsistent between two of the endpoints. |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:05 UTC | 168.3 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:10 UTC | 49.0 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:13 UTC | 90.0 | fail | Task abandoned by the agent with no artifact produced. |
| R04 | P06 | Background jobs | 14 Aug 2026 08:16 UTC | 134.8 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:21 UTC | 100.5 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:24 UTC | 88.7 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:28 UTC | 85.4 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 56.1 | pass | |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:02 UTC | 115.5 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:06 UTC | 73.8 | fail | Agent looped on the same edit for the full timeout window of 20 minutes. |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:10 UTC | 152.4 | partial | Error envelope inconsistent between two of the endpoints. |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:14 UTC | 179.4 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:19 UTC | 100.7 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:23 UTC | 83.2 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:26 UTC | 105.1 | fail | Generated migration conflicted with the existing schema and was not reconciled. |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:30 UTC | 45.2 | pass |
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, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Convex Chef pricing page | https://convex.dev/pricing | 14 Aug 2026 |
| Convex Chef product site | https://convex.dev | 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.
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.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 75.0 | 77.7 | 3 | |
| Reliability | 18% | 60.0 | 56.7 | 3 | |
| Scalability | 13% | 84.0 | 85.3 | 3 | |
| SEO and GEO | 12% | 65.0 | 66.7 | 3 | |
| API and MCP | 9% | 82.0 | 82.0 | 3 | |
| Integrations | 8% | 72.0 | 72.3 | 3 | |
| Speed | 7% | 35.4 | 37.7 | 3 | |
| Value | 5% | 78.0 | 79.0 | 2 | |
| Code ownership | 3% | 88.0 | 94.0 | 3 |
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.