Coding agents / rank 14 of 17 / cycle 04
Codebuff benchmark
A terminal agent that spreads a task over several specialised sub agents, which keeps the median low and occasionally produces two edits that disagree with each other. Three of the five recorded conflicts of that kind were caught by its own review step. Fast, cheap enough, and best on well bounded tasks rather than open ended ones.
Composite index
64.51
of 100 | withheld vs. cycle 03
Delta not shown for cycle 04: the roster was re-based from one merged ranking into two class boards, so cycle 03 and cycle 04 ranks are not on the same scale. Resumes cycle 05.
At a glance
Composite index
64.51
rank 14 of 17
Rank
#14
of 17 on the coding agents board
Median turn latency
59.8 s per prompt
9.0 min across the full nine prompt spec, derived
Reliability
68.9%
strict pass rate
SEO score
55.0
0 to 100, SEO and GEO axis
Three strongest axes
- Agent performance76.0
- Reliability68.9
- Scalability68.0
Three weakest axes
- Value52.0
- Turn latency score52.5
- SEO and GEO55.0
Median turn latency
59.8 s per prompt
p10 36.1 s, p90 110.7 s
Strict pass rate
68.9%
31 pass, 7 partial, 7 fail
Executions recorded
45
5 runs of 9 prompts
Entry price
USD 100 / month minimum subscription
Vendor's own unit and billing period. Never a currency conversion
Per axis subscores
Composite recomputed from these 9 rows: 64.51. That is the arithmetic behind the index, and you can repeat it by hand. Rounding rule: half up at two decimals, applied uniformly to all 37 published products. Code ownership has no row here: it is not scored on this board.
| Axis | Subscore 0 to 100, tick is the roster median | Score | Median | Weight % | Contribution |
|---|---|---|---|---|---|
| Reliability | 68.9 | 75.6 | 18.56 | 12.79 | |
| Agent performance | 76.0 | 80.0 | 18.55 | 14.10 | |
| Scalability | 68.0 | 74.0 | 13.4 | 9.11 | |
| SEO and GEO | 55.0 | 56.0 | 12.37 | 6.80 | |
| API and MCP | 64.0 | 70.0 | 9.28 | 5.94 | |
| Integrations | 62.0 | 70.0 | 8.25 | 5.12 | |
| Design output | 58.0 | 62.0 | 7.22 | 4.19 | |
| Turn latency score | 52.5 | 39.9 | 7.22 | 3.79 | |
| Value | 52.0 | 80.0 | 5.15 | 2.68 |
Turn latency distribution
Every recorded prompt duration for Codebuff, in seconds. Median wall clock time for one prompt, not for a whole build. The cyan tick on the whisker is the median.
Spread against the cohort
p10 36.1 s / median 59.8 s / p90 110.7 s
Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.85x.
Outcome split
31 pass / 7 partial / 7 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
18.0 KB
18,432 bytes of real text content with scripts blocked
LCP
1,900 ms
Throttled connection, cold cache
CLS
0.050
Cumulative layout shift on load
SEO and GEO subscore
55.0
0 to 100, worth 12.37 index points on this board
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 | 49.4 | pass | |
| R01 | P02 | Authentication and session | 11 Aug 2026 08:02 UTC | 59.8 | pass | |
| R01 | P03 | Projects CRUD with tenancy | 11 Aug 2026 08:05 UTC | 161.6 | pass | |
| R01 | P04 | Public REST API with keys | 11 Aug 2026 08:10 UTC | 113.7 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R01 | P05 | Outbound webhooks with signatures | 11 Aug 2026 08:14 UTC | 71.9 | pass | |
| R01 | P06 | Background jobs | 11 Aug 2026 08:17 UTC | 136.9 | pass | |
| R01 | P07 | Admin panel | 11 Aug 2026 08:21 UTC | 45.8 | pass | |
| R01 | P08 | Public marketing surface | 11 Aug 2026 08:24 UTC | 74.7 | pass | |
| R01 | P09 | Hardening pass | 11 Aug 2026 08:27 UTC | 35.1 | pass | |
| R02 | P01 | Tenant and user model | 12 Aug 2026 08:00 UTC | 44.6 | pass | |
| R02 | P02 | Authentication and session | 12 Aug 2026 08:02 UTC | 91.9 | pass | |
| R02 | P03 | Projects CRUD with tenancy | 12 Aug 2026 08:06 UTC | 32.7 | partial | Two sub agents produced conflicting edits to the same policy file. The review step caught it and reconciled one of them. |
| R02 | P04 | Public REST API with keys | 12 Aug 2026 08:08 UTC | 86.2 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R02 | P05 | Outbound webhooks with signatures | 12 Aug 2026 08:12 UTC | 82.0 | pass | |
| R02 | P06 | Background jobs | 12 Aug 2026 08:15 UTC | 58.6 | pass | |
| R02 | P07 | Admin panel | 12 Aug 2026 08:18 UTC | 88.9 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R02 | P08 | Public marketing surface | 12 Aug 2026 08:22 UTC | 53.4 | partial | Required one clarifying instruction before the criterion was met. |
| R02 | P09 | Hardening pass | 12 Aug 2026 08:24 UTC | 106.1 | pass | |
| R03 | P01 | Tenant and user model | 13 Aug 2026 08:00 UTC | 80.6 | partial | Validation added on the write path only. Read path left unguarded. |
| R03 | P02 | Authentication and session | 13 Aug 2026 08:03 UTC | 39.8 | partial | Delivered the main path, missed the boundary case named in the pass criteria. |
| R03 | P03 | Projects CRUD with tenancy | 13 Aug 2026 08:06 UTC | 59.6 | partial | Two sub agents produced conflicting edits to the same policy file. The review step caught it and reconciled one of them. |
| R03 | P04 | Public REST API with keys | 13 Aug 2026 08:09 UTC | 80.9 | pass | |
| R03 | P05 | Outbound webhooks with signatures | 13 Aug 2026 08:12 UTC | 57.2 | pass | |
| R03 | P06 | Background jobs | 13 Aug 2026 08:15 UTC | 54.6 | pass | |
| R03 | P07 | Admin panel | 13 Aug 2026 08:18 UTC | 79.6 | pass | |
| R03 | P08 | Public marketing surface | 13 Aug 2026 08:21 UTC | 40.3 | pass | |
| R03 | P09 | Hardening pass | 13 Aug 2026 08:24 UTC | 39.3 | pass | |
| R04 | P01 | Tenant and user model | 14 Aug 2026 08:00 UTC | 23.9 | partial | Pagination off by one at the final page boundary. |
| R04 | P02 | Authentication and session | 14 Aug 2026 08:02 UTC | 99.1 | fail | Task abandoned by the agent with no artifact produced. |
| R04 | P03 | Projects CRUD with tenancy | 14 Aug 2026 08:06 UTC | 74.5 | partial | Two sub agents produced conflicting edits to the same policy file. The review step caught it and reconciled one of them. |
| R04 | P04 | Public REST API with keys | 14 Aug 2026 08:09 UTC | 56.6 | pass | |
| R04 | P05 | Outbound webhooks with signatures | 14 Aug 2026 08:12 UTC | 41.3 | pass | |
| R04 | P06 | Background jobs | 14 Aug 2026 08:14 UTC | 83.0 | pass | |
| R04 | P07 | Admin panel | 14 Aug 2026 08:18 UTC | 85.5 | pass | |
| R04 | P08 | Public marketing surface | 14 Aug 2026 08:21 UTC | 60.0 | pass | |
| R04 | P09 | Hardening pass | 14 Aug 2026 08:24 UTC | 44.2 | pass | |
| R05 | P01 | Tenant and user model | 15 Aug 2026 08:00 UTC | 30.9 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R05 | P02 | Authentication and session | 15 Aug 2026 08:02 UTC | 53.9 | pass | |
| R05 | P03 | Projects CRUD with tenancy | 15 Aug 2026 08:05 UTC | 28.7 | pass | |
| R05 | P04 | Public REST API with keys | 15 Aug 2026 08:07 UTC | 37.6 | pass | |
| R05 | P05 | Outbound webhooks with signatures | 15 Aug 2026 08:10 UTC | 205.1 | fail | Build did not start after deploy. Recorded as a fail with the log preserved. |
| R05 | P06 | Background jobs | 15 Aug 2026 08:15 UTC | 42.7 | pass | |
| R05 | P07 | Admin panel | 15 Aug 2026 08:18 UTC | 61.7 | pass | |
| R05 | P08 | Public marketing surface | 15 Aug 2026 08:21 UTC | 75.8 | pass | |
| R05 | P09 | Hardening pass | 15 Aug 2026 08:24 UTC | 133.0 | fail | Generated migration conflicted with the existing schema and was not reconciled. |
Pricing
Free credits to start, then from USD 100 per month minimum subscription with usage based credits.
- Entry price
- USD 100 / month minimum subscription
- Priced from
- vendor pricing page
- Value subscore
- 52.0
- Index points per euro
- 0.75
Entry price is the vendor's own published figure, fetched 21 Aug 2026, never a currency conversion. The currency label is the vendor's own except where the pricing note above records that this lab inferred it. Index points per euro is computed from a separate, euro-normalised figure used only for the Value axis: Converted at the European Central Bank euro reference rate of 1.1699 US dollars to the euro, August 21, 2026.
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
- Written, signing on request
- 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
Codebuff landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.
Codebuff, captured 14 Aug 2026.
Sources and fetch dates
Every claim on this page traces to one of these.
| Source | URL | Fetched |
|---|---|---|
| Codebuff pricing page | https://codebuff.com/pricing | 14 Aug 2026 |
| Codebuff product site | https://codebuff.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 3.2 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.
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
64.51
1 readers have scored 88% of the index weight so far. A reader index is published at 3 voters and 50% coverage.
Seeded at launch
The reader scores, lab notes and open ratings published here were written by this lab in August 2026 to populate the reader column before the site had readers. They are not customer submissions, they are not vendor supplied and nobody was paid for them. Anything submitted since then comes from a registered account. The lab index is measured from logged runs and is unaffected either way.
| Axis | Weight | Lab | Readers | Votes | Reader mean |
|---|---|---|---|---|---|
| Agent performance | 18.55% | 76.0 | 78.0 | 1 | |
| Reliability | 18.56% | 68.9 | 67.0 | 1 | |
| Scalability | 13.4% | 68.0 | 67.0 | 1 | |
| API and MCP | 9.28% | 64.0 | 62.0 | 1 | |
| Integrations | 8.25% | 62.0 | 61.0 | 1 | |
| Design output | 7.22% | 58.0 | 58.0 | 1 | |
| Turn latency score | 7.22% | 52.5 | 59.0 | 1 | |
| Value | 5.15% | 52.0 | 84.0 | 1 |
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
64.51
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
A terminal agent that spreads a task over several specialised sub agents, which keeps the median low and occasionally produces two edits that disagree with each other. Three of the five recorded conflicts of that kind were caught by its own review step. Fast, cheap enough, and best on well bounded tasks rather than open ended ones.
Across 45 recorded executions this product met the published pass criterion cleanly 31 times, partially 7 times and failed 7 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.