AigeoRadar

AigeoRadar · AI Context Benchmark

AI Context Benchmark

Question → sufficient layer(s) → retrieved slice → measured cost → evidence

Sıcak Daldırma Galvaniz

https://kapadokyagalvaniz.com.tr/civata-sicak-daldirma-galvaniz

7 questions Answer LLM: gpt-4o-mini ai_context_benchmark_v1

Of 7 questions: lowest measured retrieval cost among sufficient layers — HTML 1 · Schema 1 · AIPM 5 · multi-layer 0 · unanswered 0. Descriptive counts only; no overall ranking.

Of 7 questions: lowest measured retrieval cost among sufficient layers — HTML 1 · Schema 1 · AIPM 5 · multi-layer 0 · unanswered 0. Descriptive counts only; no overall ranking. Each question shows: sufficient layer(s) → retrieved slice → measured input tokens → evidence. Readers interpret; the report does not rank formats. Semantic Redundancy 65% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

Gold mode · Mixed independent + AIPM consistency

Most Understanding/Retrieval gold comes from HTML. Some questions remain AIPM self-consistency checks (tagged) and are excluded from Understanding when possible. Matching a machine card against its own fields is not evidence that that layer outperforms HTML.

Execution provenance

Methodology
AI Context Benchmark Methodology v1.0
Planner Spec
v1.0
Execution Protocol
v1.0
Question pack
universal_v1
Score version
aipm_benchmark_score_v10
Engine
aipm_benchmark_v4
Answer LLM
openai / gpt-4o-mini (single provider this lab)
Model snapshot
2026-07
Run id
28676124-e51a-4eba-93a9-41e471c1facf

Question outcomes

Per question: which layers were sufficient, and what was the lowest measured retrieval cost among them. No overall winner.

1

Lowest cost: HTML

1

Lowest cost: Schema

5

Lowest cost: AIPM

0

Multi-layer

0

Unanswered

Manifest design

Semantic Redundancy · 65%

Semantic Redundancy 65% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

  • →Merge or differentiate `purpose` and `abstract` (100% overlap).
Field A Field B Overlap
purpose abstract 100%
purpose keyFacts 47%
abstract keyFacts 47%

Structural size (secondary)

Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.

HTML · 6,527 chars
Schema · 1,595 chars
AIPM · 7,944 chars

Routing helper (secondary)

Illustrative card-first vs HTML-always simulation — prefer per-question measured cost above. Not a ranking.

Card-first retrieval is roughly token-neutral vs HTML-always on this pack.

Orientation pack

7 questions · all layers scored

  • HTML 6/7
  • Schema 3/7
  • AIPM 6/7

Depth pack

0 questions · all layers scored

  • HTML 0/0
  • Schema 0/0
  • AIPM 0/0

Full-context pack metrics (secondary)

These measure the whole file fed to the model this run — not the minimum slice needed per question.

HTML

6/7 matched

22,243 full-pack tokens

Schema

3/7 matched

5,609 full-pack tokens

AIPM

6/7 matched

24,732 full-pack tokens

Full-pack resource table (secondary)

Whole-file context fed this run. Prefer Minimal Retrieval Cost on each question.

Metric HTML Schema AIPM
Coverage (matched) 6/7 3/7 6/7
Context size 6,527 chars 1,595 chars 7,944 chars
Total tokens 22,243 5,609 24,732
Tokens / correct answer 3,707 1,870 4,122
Est. cost / correct answer $0.000571 $0.000297 $0.000633
Matched per 1k tokens 0.270 0.535 0.243
Median latency 1,145 ms 832 ms 881 ms
Est. cost (USD) $0.00343 $0.00089 $0.00380

Six independent scores

Answer Efficiency is the primary cost lens. Accuracy axes remain for research — no combined total or winner.

Answer Efficiency

Matched answers per 1k tokens (and cost per match). The primary efficiency axis — not raw accuracy.

  • HTML 50.5
  • Schema 100
  • AIPM 45.4

Understanding

Can this layer convey what the page is about — using independent HTML gold?

  • HTML 100
  • Schema 75
  • AIPM 100

Retrieval

Can this layer surface shared facts (location, contact, hours, pricing, FAQ, CTA)?

  • HTML —
  • Schema —
  • AIPM —

Evidence

Answer quality vs independent gold (score strength). Partial credit counts; UNKNOWN scores zero unless gold is UNKNOWN.

  • HTML 89.4
  • Schema 45.3
  • AIPM 73.4

Metadata

Language, page kind, and freshness from page signals.

  • HTML 100
  • Schema 0
  • AIPM 50

Compression

Information delivered per token and context size. Higher means more matched answers for less context cost.

  • HTML 50.5
  • Schema 100
  • AIPM 45.4

Coverage map

AIPM matched 6 question(s) (alone on Q5); HTML matched 6. HTML/Schema (or a gap) still needed on Q3. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 6/7 matched (≈3,707 tok/match). Schema 3/7 matched (≈1,870 tok/match). AIPM 6/7 matched (≈4,122 tok/match). Figures are descriptive per layer — not a ranking. See per-question chains for sufficient layers, slice size, and measured cost.

AIPM matched

Q1, Q2, Q4, Q5, Q6, Q7

Alone: Q5

AIPM insufficient

Q3

HTML/Schema needed or all layers missed

Unanswered by all

—

HTML layer

Visible page text after stripping AIPM sidecars and JSON-LD. Measures what prose alone can answer.

Context fed: 6,527 chars

Tokens: 22,243 · median 1,145 ms

Matched this pack: 6/7

Stronger on

Understanding (100) · Metadata (100) · Evidence (89.4)

Weaker on

—

Schema layer

JSON-LD structured data with minimal page chrome. Measures what schema markup can answer.

Context fed: 1,595 chars

Tokens: 5,609 · median 832 ms

Matched this pack: 3/7

Stronger on

Understanding (75) · Compression (100) · Answer Efficiency (100)

Weaker on

Metadata (0)

AIPM layer

AI Page Manifest (.ai.json) only. Measures what the machine layer can answer without HTML.

Context fed: 7,944 chars

Tokens: 24,732 · median 881 ms

Matched this pack: 6/7

Stronger on

Understanding (100) · Evidence (73.4)

Weaker on

—

When to use which layer

AIPM complements HTML — it does not replace full-page prose.

Scenario Recommended Why
Fast orientation (title, purpose, brand, intent) Compare machine card → HTML fallback on this run Machine-card pack: 24,732 tok · $0.00380.
Deep content / research (prose facts, process detail) HTML (with optional machine orientation) HTML pack: 22,243 tok · $0.00343. Use when depth needs body prose.
Structured entity pulls (org, location, typed fields) Schema.org Schema pack: 5,609 tok · $0.00089. Dense JSON-LD tends to score well here.

Findings

  • —Of 7 questions: lowest measured retrieval cost among sufficient layers — HTML 1 · Schema 1 · AIPM 5 · multi-layer 0 · unanswered 0. Descriptive counts only; no overall ranking.
  • —Semantic Redundancy 65% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.
  • —Manifest design: Merge or differentiate `purpose` and `abstract` (100% overlap).
  • —Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.
  • —AIPM matched 6 question(s) (alone on Q5); HTML matched 6. HTML/Schema (or a gap) still needed on Q3. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 6/7 matched (≈3,707 tok/match). Schema 3/7 matched (≈1,870 tok/match). AIPM 6/7 matched (≈4,122 tok/match). Figures are descriptive per layer — not a ranking. See per-question chains for sufficient layers, slice size, and measured cost.

Question-by-question layer analysis

Which layer(s) could answer; which need more or different context; minimum context fed this run.

Q1 · Understanding · orientation

What is the purpose of this page?

Gold: Cıvatalar İçin Sıcak Daldırma Galvanizleme Uygulamaları Civata sıcak daldırma galvaniz, özellikle şu alanlarda yaygın olarak kullanılır ⟶ İnşaat Binaların iskelet yapısında kullanılan cıvatalar Otomotiv Araç montajında kullanılan cıvatalar.

Gold source: purpose · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Estimated retrieval cost · lowest cost AIPM · 40 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.lead_paragraphs 187 est — — yes
Schema jsonld.description — est — — no
AIPM purpose 40 est — — yes

HTML

sufficient

The purpose of this page is to provide information about civata sıcak daldırma galvaniz (hot dip galvanizing of bolts) services offered by Kapadokya Galvaniz.

score 80 · 6,527 chars context · 2,204 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN.

score 0 · 1,595 chars context · 550 in-tokens

Schema did not answer from 1595 chars of context — additional or different layer context needed.

AIPM

sufficient

The purpose of this page is to provide durable and long-lasting solutions for hot-dip galvanizing of bolts used in construction, automotive, machinery, and various other industries.

score 100 · 7,944 chars context · 2,454 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Q2 · Understanding · orientation

What is the page title?

Gold: Civata Sıcak Daldırma Galvaniz – Kapadokya Galvaniz

Gold source: title · html_independent

Sufficient: HTML, Schema, AIPM

Estimated retrieval cost · lowest cost SCHEMA · 5 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.title 13 est — — yes
Schema jsonld.name 5 est — — yes
AIPM title 8 est — — yes

HTML

sufficient

Civata Sıcak Daldırma Galvaniz – Kapadokya Galvaniz

score 100 · 6,527 chars context · 2,202 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

sufficient

The page title is "Civata Sıcak Daldırma Galvaniz – Kapadokya Galvaniz."

score 92 · 1,595 chars context · 548 in-tokens

Schema answered using 1595 chars of layer context (minimum fed this run).

AIPM

sufficient

The page title is "Civata Sıcak Daldırma Galvaniz."

score 80 · 7,944 chars context · 2,452 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Q3 · Metadata · orientation

What language is this page in?

Gold: tr

Gold source: inLanguage · html_independent

Sufficient: HTML · Needs more / other context: Schema, AIPM

Estimated retrieval cost · lowest cost HTML · 2 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.lang 2 est — — yes
Schema jsonld.block — est — — no
AIPM inLanguage — est — — no

Root cause · Layer miss

Improve orientation fields; do not paste full HTML into the sidecar.

HTML

sufficient

The page is in Turkish.

score 88 · 6,527 chars context · 2,203 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN.

score 0 · 1,595 chars context · 549 in-tokens

Schema did not answer from 1595 chars of context — additional or different layer context needed.

AIPM

insufficient

The page is in English.

score 0 · 7,944 chars context · 2,453 in-tokens

AIPM did not answer from 7944 chars of context — additional or different layer context needed.

Q4 · Understanding · orientation

What is the primary topic of this page?

Gold: Civata Sıcak Daldırma Galvaniz

Gold source: primaryTopic · html_independent

Sufficient: HTML, Schema, AIPM

Estimated retrieval cost · lowest cost AIPM · 8 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.h1|title 8 est — — yes
Schema No typed Schema field for this question. — est — — yes
AIPM primaryTopic 8 est — — yes

HTML

sufficient

The primary topic of this page is "Civata Sıcak Daldırma Galvaniz" (Bolt Hot Dip Galvanizing).

score 80 · 6,527 chars context · 2,205 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

sufficient

The primary topic of this page is "Civata Sıcak Daldırma Galvaniz" related to Kapadokya Galvaniz.

score 80 · 1,595 chars context · 551 in-tokens

Schema answered using 1595 chars of layer context (minimum fed this run).

AIPM

sufficient

The primary topic of this page is "Civata Sıcak Daldırma Galvaniz."

score 84 · 7,944 chars context · 2,455 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Q5 · Understanding · orientation

Who is the intended audience declared in AIPM?

Gold: Metal Kaplama & Galvaniz hizmetleriyle ilgilenen firmalar, şahıslar

Gold source: audience · aipm_consistency

Sufficient: AIPM

Estimated retrieval cost · lowest cost AIPM · 18 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.lead — est — — no
Schema No typed Schema field for this question. — est — — no
AIPM audience 18 est — — yes

HTML

skipped

The intended audience includes industries such as construction, automotive, machinery, and maritime that require durable and corrosion-resistant fasteners.

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

Schema

skipped

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

AIPM

sufficient

The intended audience includes "Metal Kaplama & Galvaniz hizmetleriyle ilgilenen firmalar" and "şahıslar."

score 82 · 7,944 chars context · 2,452 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Q6 · Understanding · orientation

Who is the publisher or brand?

Gold: Kapadokya Galvaniz

Gold source: publisher.name · html_independent

Sufficient: HTML, Schema, AIPM

Estimated retrieval cost · lowest cost AIPM · 5 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.title_brand 13 est — — yes
Schema jsonld.name 5 est — — yes
AIPM publisher 5 est — — yes

HTML

sufficient

Kapadokya Galvaniz.

score 100 · 6,527 chars context · 2,203 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

sufficient

Kapadokya Galvaniz.

score 100 · 1,595 chars context · 549 in-tokens

Schema answered using 1595 chars of layer context (minimum fed this run).

AIPM

sufficient

The publisher is Kapadokya Galvaniz.

score 88 · 7,944 chars context · 2,453 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Q7 · Metadata · orientation

What is the content intent?

Gold: commercial

Gold source: contentIntent · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Estimated retrieval cost · lowest cost AIPM · 3 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML html.prose_signals 100 est — — yes
Schema No typed Schema field for this question. — est — — no
AIPM contentIntent 3 est — — yes

HTML

sufficient

The content intent is to promote and provide information about hot-dip galvanizing services for bolts and other industrial applications offered by Kapadokya Galvaniz.

score 88 · 6,527 chars context · 2,202 in-tokens

HTML answered using 6527 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 1,595 chars context · 548 in-tokens

Schema did not answer from 1595 chars of context — additional or different layer context needed.

AIPM

sufficient

The content intent is commercial.

score 88 · 7,944 chars context · 2,452 in-tokens

AIPM answered using 7944 chars of layer context (minimum fed this run).

Methodology

  • AI Context Benchmark: Planner → Slice → LLM with measured API input tokens.
  • Reports describe sufficient layers, slice size, cost, and evidence — they do not declare a winning format.
  • Layers under test today: HTML, Schema.org, AIPM (extensible to RSS, Markdown, PDF, …).
  • Engine aipm_benchmark_v1 · Tue, Jul 28, 2026 9:49 PM · aipm_benchmark_score_v10

Share

Per-question context chain across layers.

Post on X LinkedIn WhatsApp
About the lab →