API
AI IQ publishes a small JSON API for public model, benchmark, ranking, chart, and methodology metadata. The API is designed for simple read-only integrations and returns sanitized public fields only.
The canonical base URL is https://www.aiiq.org. The listed GET endpoints return JSON. AI IQ also exposes a remote MCP connector for agents at https://www.aiiq.org/api/mcp.
Endpoints
Public model summaries with rank, IQ, per-dimension IQ scores, cost block, update timestamp, and canonical URL.
Detailed public data for one model, including source-backed benchmark results.
Benchmark metadata with stable IDs, names, categories, update timestamp, and public URL.
Derived rankings and per-benchmark rankings with score, rank, direction, provider, and model profile URL.
Canonical chart metadata, related benchmarks, and tags.
Public methodology metadata with version, derived ranking hierarchy, timestamp, and URL.
Remote Model Context Protocol connector for agents and Claude custom connectors. This is a Streamable HTTP MCP endpoint, not a browser JSON endpoint.
curl https://www.aiiq.org/api/models curl https://www.aiiq.org/api/models/gpt-5.5 curl https://www.aiiq.org/api/benchmarks curl https://www.aiiq.org/api/rankings curl https://www.aiiq.org/api/charts curl https://www.aiiq.org/api/methodology
MCP Connector
Agents and MCP clients can connect to AI IQ's hosted MCP server with this remote server URL:
https://www.aiiq.org/api/mcp
Use that URL in clients that support remote MCP or Claude custom connectors. In Claude, add a custom connector and paste the URL above as the remote MCP server URL. In other agent clients, choose the remote or Streamable HTTP MCP option and use the same URL.
Name: AI IQ URL: https://www.aiiq.org/api/mcp Type: Remote MCP / Streamable HTTP
The connector exposes read-only tools for listing models, fetching model details, listing and fetching rankings, listing benchmarks, reading methodology metadata, and comparing models.
/api/mcp is a Streamable HTTP MCP transport endpoint. It is discoverable after a client is explicitly configured with the URL, but it is not a normal web page or JSON API route to open directly in a browser.
Models
GET /api/models returns a list of public model summaries. Every response is wrapped in an envelope with apiVersion, methodologyVersion, updatedAt, and a models array.
| Field | Description |
|---|---|
| id | Stable model identifier, matching the model name slug used by AI IQ. |
| name | Human-readable model name. |
| provider | Public provider grouping used in charts. |
| rank | Current Composite IQ rank when the model has a derived IQ. |
| iq | Rounded Composite IQ, or null when the model is not ranked. |
| dimensions | Compact map from scored dimension slug to rounded dimension IQ score. Seven entries in dimension order: mathematical-reasoning, scientific-reasoning, abstract-reasoning, app-building, production-engineering, computer-use, reliability. Each value is null when the dimension cannot be computed for that model. |
| emotionalReasoning | Experimental diagnostic Emotional Reasoning (EQ) score, excluded from Composite IQ, or null. |
| cost | Cost block: inputPer1M, outputPer1M, ioPer1M, usageMultiplier, effectivePer1M, unit ("USD per 1M I/O Tokens"). null when pricing is unavailable. |
| updatedAt | ISO timestamp derived from the newest model or benchmark data file. |
| url | Canonical public AI IQ model profile URL. |
{
"apiVersion": "1",
"methodologyVersion": "2026-07-03-gso-bench",
"updatedAt": "2026-06-08T00:00:00.000Z",
"models": [
{
"id": "gpt-5.5",
"name": "gpt-5.5",
"provider": "OpenAI",
"rank": 3,
"iq": 129,
"dimensions": {
"mathematical-reasoning": 141,
"scientific-reasoning": 142,
"abstract-reasoning": 108,
"app-building": 125,
"production-engineering": 134,
"computer-use": 135,
"reliability": 119
},
"emotionalReasoning": 118,
"cost": {
"inputPer1M": 5,
"outputPer1M": 30,
"ioPer1M": 35,
"usageMultiplier": 1.033,
"effectivePer1M": 36.1393,
"unit": "USD per 1M I/O Tokens"
},
"updatedAt": "2026-06-08T00:00:00.000Z",
"url": "https://www.aiiq.org/models/gpt-5.5/"
}
]
}Benchmarks
GET /api/benchmarks returns metadata for scored IQ benchmarks and experimental EQ diagnostic benchmarks. Benchmark scores and rankings are exposed through GET /api/rankings.
| Field | Description |
|---|---|
| id | Stable benchmark identifier used in benchmark results and rankings. |
| name | Human-readable benchmark name. |
| description | Plain-text description when available. |
| category | Benchmark category: iq for scored IQ benchmarks, eq for diagnostic emotional-reasoning benchmarks (Arena Elo, AttuneBench Composite, EQ-Bench 3 Elo). |
| dimension | The scored dimension slug this benchmark contributes to (e.g. abstract-reasoning), or null for diagnostic EQ benchmarks. |
| direction | higher_is_better or lower_is_better. |
| unit | Unit string when available (e.g. percent, Elo), or null. |
| updatedAt | ISO timestamp derived from the newest model or benchmark data file. |
| url | Public chart or chart-gallery URL associated with the benchmark. |
{
"apiVersion": "1",
"methodologyVersion": "2026-07-03-gso-bench",
"updatedAt": "2026-06-08T00:00:00.000Z",
"benchmarks": [
{
"id": "arc-agi-2",
"name": "ARC-AGI-2",
"description": "",
"category": "iq",
"dimension": "abstract-reasoning",
"direction": "higher_is_better",
"unit": "percent",
"updatedAt": "2026-06-08T00:00:00.000Z",
"url": "https://www.aiiq.org/charts/"
}
]
}Model Detail
GET /api/models/:id returns a single public model with the full dimensions block, cost block, all benchmark results, and the methodology version. The envelope is the same as other endpoints (apiVersion, methodologyVersion, updatedAt) with model fields at the top level.
The dimensions block here is the full form (vs. the compact slug→iq map on /api/models): each entry includes iq, benchmarksCovered, benchmarksTotal, and imputed. Each benchmarkResults entry includes dimension and direction in addition to value, field, name, and category.
{
"apiVersion": "1",
"methodologyVersion": "2026-07-03-gso-bench",
"updatedAt": "2026-06-08T00:00:00.000Z",
"id": "gpt-5.5",
"name": "gpt-5.5",
"provider": "OpenAI",
"rank": 3,
"iq": 129,
"dimensions": {
"mathematical-reasoning": {
"iq": 141,
"benchmarksCovered": 4,
"benchmarksTotal": 5,
"imputed": false
},
"scientific-reasoning": {
"iq": 142,
"benchmarksCovered": 4,
"benchmarksTotal": 4,
"imputed": false
},
"abstract-reasoning": {
"iq": 108,
"benchmarksCovered": 3,
"benchmarksTotal": 3,
"imputed": false
},
"app-building": {
"iq": 125,
"benchmarksCovered": 4,
"benchmarksTotal": 4,
"imputed": false
},
"production-engineering": {
"iq": 134,
"benchmarksCovered": 7,
"benchmarksTotal": 8,
"imputed": false
}
},
"emotionalReasoning": 118,
"cost": {
"inputPer1M": 5,
"outputPer1M": 30,
"ioPer1M": 35,
"usageMultiplier": 1.033,
"effectivePer1M": 36.1393,
"unit": "USD per 1M I/O Tokens"
},
"url": "https://www.aiiq.org/models/gpt-5.5/",
"benchmarkResults": {
"arc-agi-2": {
"value": 85,
"field": "arcAgi2",
"name": "ARC-AGI-2",
"category": "iq",
"dimension": "abstract-reasoning",
"direction": "higher_is_better"
},
"eq-bench-3-elo": {
"value": 1596.5,
"field": "eqBenchElo",
"name": "EQ-Bench 3 Elo",
"category": "eq",
"dimension": null,
"direction": "higher_is_better"
}
}
}Rankings
GET /api/rankings returns all rankings in one list. Use rankingType to distinguish types. The order is: composite-iq (derived), effective-cost (derived), seven dimension IQ rankings (type dimension, ordered from mathematical-reasoning-iq through reliability-iq), then per-benchmark rankings (type benchmark). Composite IQ is higher-is-better; Effective Cost is lower-is-better. The Composite EQ ranking was retired; Emotional Reasoning (EQ) is an experimental diagnostic field and source-benchmark group, not a dimension ranking.
| Field | Description |
|---|---|
| id | Stable ranking identifier. Dimension rankings use the pattern <slug>-iq. |
| rankingName | Human-readable ranking name. |
| rankingType | derived for Composite IQ and Effective Cost; dimension for per-dimension IQ rankings; benchmark for source-backed benchmark rankings. |
| dimension | Dimension slug — present on dimension rankings and scored benchmark rankings. Diagnostic EQ benchmark rankings use null. |
| field | Source data field, present on benchmark rankings. |
| category | Benchmark category (e.g. iq, eq, cost), present on benchmark rankings. |
| methodologyVersion | Present on derived and dimension rankings. |
| direction | higher_is_better or lower_is_better. |
| unit | Present when the ranking has an explicit unit. |
| models | Ranked model rows with id, name, provider, rank, score. Dimension rankings also include imputed. Benchmark rankings also include url. |
{
"apiVersion": "1",
"methodologyVersion": "2026-07-03-gso-bench",
"updatedAt": "2026-06-08T00:00:00.000Z",
"rankings": [
{
"id": "composite-iq",
"rankingName": "Composite IQ",
"rankingType": "derived",
"methodologyVersion": "2026-07-03-gso-bench",
"direction": "higher_is_better",
"models": [
{ "id": "gpt-5.5", "name": "gpt-5.5", "provider": "OpenAI", "rank": 3, "score": 129 }
]
},
{
"id": "effective-cost",
"rankingName": "Effective Cost",
"rankingType": "derived",
"methodologyVersion": "2026-07-03-gso-bench",
"direction": "lower_is_better",
"unit": "USD per 1M I/O Tokens",
"models": [
{ "id": "gpt-oss-20b", "name": "gpt-oss-20b", "provider": "OpenAI", "rank": 1, "score": 0.2056 }
]
},
{
"id": "mathematical-reasoning-iq",
"rankingName": "Mathematical Reasoning IQ",
"rankingType": "dimension",
"dimension": "mathematical-reasoning",
"methodologyVersion": "2026-07-03-gso-bench",
"direction": "higher_is_better",
"models": [
{ "id": "gpt-5.5", "name": "gpt-5.5", "provider": "OpenAI", "rank": 1, "score": 141, "imputed": false }
]
]
},
{
"id": "aime",
"rankingName": "AIME",
"rankingType": "benchmark",
"field": "aime",
"category": "iq",
"dimension": "mathematical-reasoning",
"direction": "higher_is_better",
"models": [
{ "id": "gemini-3.1-pro", "name": "gemini-3.1-pro", "provider": "Google", "rank": 1, "score": 98.125, "url": "https://www.aiiq.org/models/gemini-3.1-pro/" }
]
}
]
}Charts
GET /api/charts returns promoted canonical chart metadata. Chart URLs are stable share pages, not rendered SVG exports. More / Experimental charts are excluded.
| Field | Description |
|---|---|
| id | Stable chart slug. |
| title | Public chart title. |
| description | Plain-text chart description. |
| url | Canonical chart page URL. |
| image | Open Graph/Twitter preview image URL for the chart. |
| relatedBenchmarks | Benchmark IDs used by the chart, when applicable. |
| tags | Category and chart-kind tags. |
Methodology
GET /api/methodology exposes public methodology metadata and the hierarchy behind the two derived rankings (Composite IQ and Effective Cost). For the full scoring explanation, use the Methodology page.
The Composite EQ standalone ranking was retired. Emotional Reasoning (EQ) is retained as an experimental diagnostic metric and benchmark group, but it is excluded from Composite IQ until the benchmark base becomes more rigorous.
Each scored dimension in the Composite IQ derivedRankings entry carries a slug field (e.g. abstract-reasoning) that matches the dimension slugs used in model detail and dimension rankings. D1 is Abstract Reasoning, D4 is App Building, and D5 is Production Engineering.
{
"apiVersion": "1",
"version": "2026-07-03-gso-bench",
"summary": "Composite IQ uses seven scored dimensions mapped through IQ 70-160 expected-score ladders, conservative imputation rules, and chart display policies documented on the methodology page. Effective Cost uses positive input/output pricing plus a measured-or-imputed usage multiplier waterfall documented on the methodology page. Emotional Reasoning (EQ) is retained as an experimental diagnostic metric and is excluded from Composite IQ until its benchmark base becomes more rigorous.",
"derivedRankings": [
{
"id": "composite-iq",
"rankingName": "Composite IQ",
"direction": "higher_is_better",
"scoreField": "iq",
"dimensions": [
{
"id": "D1",
"slug": "abstract-reasoning",
"name": "Abstract Reasoning",
"minBenchmarks": 1,
"benchmarks": [
{ "field": "arcAgi3", "name": "ARC-AGI-3" },
{ "field": "arcAgi2", "name": "ARC-AGI-2" },
{ "field": "arcAgi1", "name": "ARC-AGI-1" }
]
}
]
},
{
"id": "effective-cost",
"rankingName": "Effective Cost",
"direction": "lower_is_better",
"scoreField": "effectiveCost",
"unit": "USD per 1M I/O Tokens",
"breakdown": [
{
"id": "published-pricing",
"name": "Published Token Pricing",
"inputs": [
{ "field": "inP", "name": "Input token price" },
{ "field": "outP", "name": "Output token price" }
],
"summary": "Base cost is input price plus output price for 1M input tokens and 1M output tokens. Free, zero-dollar, or rate-limited rows remain null unless a specific nonzero hosted-provider price is recorded."
},
{
"id": "usage-multiplier-waterfall",
"name": "Usage Multiplier Waterfall",
"steps": [
"measured benchmark multiplier from validated token usage and price-adjusted task-cost residuals",
"one-generation-back same-family same-lineage multiplier",
"two-generations-back same-family same-lineage multiplier",
"geometric average of the three closest measured peers",
"assumed 1x fallback for positive-price models"
]
}
]
}
],
"updatedAt": "2026-06-08T00:00:00.000Z",
"url": "https://www.aiiq.org/methodology/"
}Privacy Boundary
The public API exposes only sanitized public data intended for read-only integrations. It omits private configuration, unpublished records, internal review metadata, and operational tooling details.