coding-agent / rank 10 of 41 / cycle 04
Replit benchmark
The most operationally complete result: a real queue, working scheduled jobs and a database that survived the 50000 row load without a rewrite. It is also the slowest of the top group because the agent runs a longer plan and test cycle. The public marketing surface was the weakest part, client rendered in 4 of 5 runs.
Composite index
73.42
of 100 | ▲ 1 versus cycle 03
At a glance
Composite index
73.42
rank 10 of 41
Rank
#10
of 41 measured builders
Median speed
135.7 s
p10 92.8 s, p90 188.8 s
Reliability
86.7%
strict pass rate
SEO score
62.0
0 to 100, SEO and GEO axis
Three strongest axes
- Reliability86.7
- Agent performance83.0
- Code ownership82.0
Three weakest axes
- Speed23.1
- SEO and GEO62.0
- Value66.0
Median per prompt
135.7 s
p10 92.8 s, p90 188.8 s
Strict pass rate
86.7%
39 pass, 4 partial, 2 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
EUR 22.00
Cheapest plan that can finish the specification
Per axis subscores
Composite recomputed from these ten rows: 73.42. 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 | 83.0 | 75.0 | 18 | 14.94 | |
| Reliability | 86.7 | 71.1 | 18 | 15.61 | |
| Scalability | 80.0 | 70.0 | 13 | 10.40 | |
| SEO and GEO | 62.0 | 58.0 | 12 | 7.44 | |
| API and MCP | 71.0 | 62.0 | 9 | 6.39 | |
| Integrations | 77.0 | 66.0 | 8 | 6.16 | |
| Design output | 73.0 | 71.0 | 7 | 5.11 | |
| Speed | 23.1 | 33.0 | 7 | 1.62 | |
| Value | 66.0 | 76.0 | 5 | 3.30 | |
| Code ownership | 82.0 | 90.0 | 3 | 2.46 |
Speed distribution
Every recorded prompt duration for Replit, in seconds. The cyan tick on the whisker is the median.
Spread against the cohort
p10 92.8 s / median 135.7 s / p90 188.8 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.39x.
Outcome split
39 pass / 4 partial / 2 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
9.0 KB
9,216 bytes of real text content with scripts blocked
LCP
2,880 ms
Throttled connection, cold cache
CLS
0.120
Cumulative layout shift on load
SEO and GEO subscore
62.0
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 | 108.5 | pass | |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:03 UTC | 95.6 | pass | |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:07 UTC | 85.9 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:10 UTC | 176.1 | pass | |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:15 UTC | 122.9 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:19 UTC | 104.6 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:23 UTC | 94.7 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:27 UTC | 192.7 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:32 UTC | 102.4 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 91.5 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:03 UTC | 109.9 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:07 UTC | 89.9 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:10 UTC | 169.6 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:15 UTC | 172.3 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:20 UTC | 197.4 | pass | |
| R02 | P07 | Admin panel | 12 Aug 2026 08:25 UTC | 77.0 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:29 UTC | 100.7 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:32 UTC | 182.9 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 123.9 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:04 UTC | 127.9 | pass | |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:08 UTC | 141.0 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:12 UTC | 169.9 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:17 UTC | 175.8 | fail | Generated migration conflicted with the existing schema and was not reconciled. |
| R03 | P06 | Background jobs | 13 Aug 2026 08:22 UTC | 178.3 | partial | Required one clarifying instruction before the criterion was met. |
| R03 | P07 | Admin panel | 13 Aug 2026 08:27 UTC | 149.4 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:31 UTC | 174.0 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:36 UTC | 150.0 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 116.2 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:03 UTC | 139.3 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:08 UTC | 135.7 | pass | |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:12 UTC | 126.9 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:16 UTC | 139.5 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:20 UTC | 214.6 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:26 UTC | 101.9 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:30 UTC | 144.1 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:34 UTC | 115.6 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 106.0 | pass | |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:03 UTC | 201.6 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:09 UTC | 96.6 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:12 UTC | 155.9 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:17 UTC | 117.7 | partial | Pagination off by one at the final page boundary. |
| R05 | P06 | Background jobs | 15 Aug 2026 08:21 UTC | 172.4 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:26 UTC | 137.5 | fail | Generated migration conflicted with the existing schema and was not reconciled. |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:30 UTC | 199.1 | pass | |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:35 UTC | 68.2 | pass |
Pricing
Free tier for prototypes. Core from EUR 22 per month including agent time, deployments and always on services.
- Entry price
- EUR 22.00
- Value subscore
- 66.0
- Index points per euro
- 3.34
Capabilities as measured
- stack
- Any, a full Linux workspace
- deploy
- Autoscale, reserved VM and scheduled deployments
- database
- Built in Postgres and key value store
- auth
- Built in identity plus libraries
- background jobs
- Yes, scheduled deployments and workers
- webhooks
- Hand written, full control
- rest api
- Hand written, full control
- mcp server
- Yes
- export code
- Full filesystem access and Git
- custom domain
- Yes
- ssr
- Depends on the framework the agent picks
Screenshot
Replit landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Replit, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Replit pricing page | https://replit.com/pricing | 14 Aug 2026 |
| Replit product site | https://replit.com | 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 3.7 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.
Replit 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
67.02
Lab index
73.42
3 readers, 25 axis scores, last change 15 Aug 2026. Readers rate Replit 6.4 points below the measurement.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 83.0 | 73.0 | 3 | |
| Reliability | 18% | 86.7 | 80.3 | 3 | |
| Scalability | 13% | 80.0 | 72.7 | 3 | |
| SEO and GEO | 12% | 62.0 | 57.7 | 3 | |
| API and MCP | 9% | 71.0 | 64.3 | 3 | |
| Integrations | 8% | 77.0 | 72.3 | 3 | |
| Speed | 7% | 23.1 | 18.7 | 3 | |
| Value | 5% | 66.0 | 66.0 | 1 | |
| Code ownership | 3% | 82.0 | 72.7 | 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
79.50
2 published open ratings, submitted without an account
Lab index
73.42
Measured, not voted
Gap to the measurement
6.08
Positive means open raters put it above the measurement
What agent performance looked like in practice
The most operationally complete result: a real queue, working scheduled jobs and a database that survived the 50000 row load without a rewrite. It is also the slowest of the top group because the agent runs a longer plan and test cycle. The public marketing surface was the weakest part, client rendered in 4 of 5 runs.
Across 45 recorded executions this product met the published pass criterion cleanly 39 times, partially 4 times and failed 2 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.