coding-agent / rank 9 of 41 / cycle 04
Amp benchmark
One of the three fastest agents in the index and the one that wasted the least time on work nobody asked for. It runs at whatever model tier it judges the task needs, which is why the duration spread is tighter than the raw speed suggests. It has no interface of its own and does not pretend otherwise, so design and SEO track the stack rather than the tool.
Composite index
74.04
of 100 | ▲ 1 versus cycle 03
At a glance
Composite index
74.04
rank 9 of 41
Rank
#9
of 41 measured builders
Median speed
39.7 s
p10 24.2 s, p90 64.4 s
Reliability
77.8%
strict pass rate
SEO score
56.0
0 to 100, SEO and GEO axis
Three strongest axes
- Code ownership98.0
- Agent performance85.0
- Speed79.1
Three weakest axes
- SEO and GEO56.0
- Design output60.0
- Integrations68.0
Median per prompt
39.7 s
p10 24.2 s, p90 64.4 s
Strict pass rate
77.8%
35 pass, 6 partial, 4 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
EUR 0.00
Cheapest plan that can finish the specification
Per axis subscores
Composite recomputed from these ten rows: 74.04. 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 | 85.0 | 75.0 | 18 | 15.30 | |
| Reliability | 77.8 | 71.1 | 18 | 14.00 | |
| Scalability | 74.0 | 70.0 | 13 | 9.62 | |
| SEO and GEO | 56.0 | 58.0 | 12 | 6.72 | |
| API and MCP | 72.0 | 62.0 | 9 | 6.48 | |
| Integrations | 68.0 | 66.0 | 8 | 5.44 | |
| Design output | 60.0 | 71.0 | 7 | 4.20 | |
| Speed | 79.1 | 33.0 | 7 | 5.54 | |
| Value | 76.0 | 76.0 | 5 | 3.80 | |
| Code ownership | 98.0 | 90.0 | 3 | 2.94 |
Speed distribution
Every recorded prompt duration for Amp, in seconds. The cyan tick on the whisker is the median.
Spread against the cohort
p10 24.2 s / median 39.7 s / p90 64.4 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.62x.
Outcome split
35 pass / 6 partial / 4 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
20.0 KB
20,480 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
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 | 68.0 | pass | |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:03 UTC | 33.5 | pass | |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:05 UTC | 64.6 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:08 UTC | 24.3 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:11 UTC | 37.9 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:13 UTC | 45.2 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:16 UTC | 60.6 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:19 UTC | 50.3 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:22 UTC | 62.0 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 39.7 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:02 UTC | 71.9 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:05 UTC | 39.6 | pass | |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:08 UTC | 69.6 | pass | |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:11 UTC | 43.7 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:14 UTC | 64.2 | partial | Error envelope inconsistent between two of the endpoints. |
| R02 | P07 | Admin panel | 12 Aug 2026 08:17 UTC | 31.7 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:20 UTC | 25.8 | pass | |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:22 UTC | 25.6 | partial | Validation added on the write path only. Read path left unguarded. |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 40.4 | pass | |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:02 UTC | 53.8 | pass | |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:05 UTC | 26.3 | pass | |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:08 UTC | 61.9 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:11 UTC | 30.7 | pass | |
| R03 | P06 | Background jobs | 13 Aug 2026 08:13 UTC | 47.4 | partial | Validation added on the write path only. Read path left unguarded. |
| R03 | P07 | Admin panel | 13 Aug 2026 08:16 UTC | 48.6 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:19 UTC | 26.1 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:21 UTC | 27.9 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 32.1 | pass | |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:02 UTC | 43.5 | pass | |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:05 UTC | 29.7 | fail | Task abandoned by the agent with no artifact produced. |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:07 UTC | 28.5 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:10 UTC | 52.5 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:13 UTC | 39.0 | partial | Error envelope inconsistent between two of the endpoints. |
| R04 | P07 | Admin panel | 14 Aug 2026 08:15 UTC | 42.9 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:18 UTC | 55.1 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:21 UTC | 18.0 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 21.5 | fail | Task abandoned by the agent with no artifact produced. |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:02 UTC | 24.1 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:04 UTC | 44.7 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:07 UTC | 53.7 | partial | Required one clarifying instruction before the criterion was met. |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:10 UTC | 32.2 | pass | |
| R05 | P06 | Background jobs | 15 Aug 2026 08:12 UTC | 65.3 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:16 UTC | 18.8 | pass | |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:18 UTC | 19.5 | pass | |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:20 UTC | 38.8 | fail | Task abandoned by the agent with no artifact produced. |
Pricing
No licence fee. Usage is metered against a prepaid balance, so a light month costs almost nothing.
- Entry price
- EUR 0.00
- Value subscore
- 76.0
- Index points per euro
- 74.04
Capabilities as measured
- stack
- Your repository, any framework
- deploy
- Not included
- database
- Whatever you already run
- auth
- It wires the library you choose
- background jobs
- Implemented in your stack
- webhooks
- Signed when the criterion names it
- rest api
- Written to your conventions
- mcp server
- Yes
- export code
- The code was never anywhere else
- custom domain
- Your hosting decides
- ssr
- Your framework decides
Screenshot
Amp landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Amp, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Amp pricing page | https://ampcode.com/pricing | 14 Aug 2026 |
| Amp product site | https://ampcode.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.
Amp 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
not rated yet
Lab index
74.04
2 readers have scored 100% of the index weight so far. A reader index is published at 3 voters and 50% coverage.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18% | 85.0 | 87.5 | 2 | |
| Reliability | 18% | 77.8 | 85.5 | 2 | |
| Scalability | 13% | 74.0 | 82.5 | 2 | |
| SEO and GEO | 12% | 56.0 | 60.0 | 1 | |
| API and MCP | 9% | 72.0 | 76.5 | 2 | |
| Integrations | 8% | 68.0 | 70.5 | 2 | |
| Design output | 7% | 60.0 | 67.0 | 2 | |
| Speed | 7% | 79.1 | 87.5 | 2 | |
| Value | 5% | 76.0 | 85.0 | 2 | |
| Code ownership | 3% | 98.0 | 100.0 | 2 |
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
74.04
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
One of the three fastest agents in the index and the one that wasted the least time on work nobody asked for. It runs at whatever model tier it judges the task needs, which is why the duration spread is tighter than the raw speed suggests. It has no interface of its own and does not pretend otherwise, so design and SEO track the stack rather than the tool.
Across 45 recorded executions this product met the published pass criterion cleanly 35 times, partially 6 times and failed 4 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.