{ "data": { "category": { "area": "everyday", "capabilities": [ "learning.quiz", "learning.flashcards", "learning.tutoring", "learning.courses", "learning.lms", "learning.progress" ], "description": "Services that make quizzes, flashcards and courses from material, hold a learner's progress, run assessments and connect to the course systems schools use, so an agent can build a revision set, mark a test or fetch an assignment for a person. Compared on what an agent can create and read, learner data and consent, what an institution has to approve and the price per learner or per item.", "json": "https://www.anchorterminal.com/categories/learning.json", "name": "Learning, tutoring \u0026 assessment", "slug": "learning", "test": "In this run, public evidence against the published checklist. When the task suites run, the same chapter turned into a ten-question quiz and a flashcard set through each listing, a learner's answers recorded and the score read back. We check the questions against the text, what the API says about the learner and what a school account has to allow.", "title": "Learning, tutoring and assessment tools for AI agents", "toolCount": 6, "tools": [ "moodle", "learnosity", "canvas-lms", "preply", "kahoot", "quizgecko" ], "url": "https://www.anchorterminal.com/categories/learning" }, "faq": [ { "answer": "Moodle has the highest benchmark score of the 6 ranked learning, tutoring and assessment tools, 67.7 (B). Learnosity is second with 60.2 (C).", "question": "What are the highest-rated learning, tutoring and assessment tools for AI agents?" }, { "answer": "0 of the 6 ranked here grade BB or better, the bar for agent-ready on the Anchor benchmark.", "question": "How many learning, tutoring and assessment tools are agent-ready?" }, { "answer": "None of the ranked listings here accepts x402 for its main call yet.", "question": "Which learning, tutoring and assessment tools accept x402 payments?" }, { "answer": "By the Anchor benchmark score out of 100, a weighted mean of the scored categories minus deductions for negative events, from public evidence re-checked as vendors change. Listings cannot pay for a place. The latest assessment behind this page is from 3 November 2026.", "question": "How is this list ranked?" } ], "howToChoose": [ { "label": "Create or read only", "detail": "Check whether the API can make a quiz or a card set from text or only returns what people made in the app, since an agent that cannot create has nothing to hand a learner." }, { "label": "Learner data and consent", "detail": "Check what the API returns about a learner and who has to consent, because school and child data carry rules the agent's operator answers for." }, { "label": "Institution approval", "detail": "Check whether a school or an administrator has to switch access on, as a course system often keeps its API behind an institution's own keys." }, { "label": "Price per learner", "detail": "Check whether the price is per learner, per seat or per item made, since a tutoring agent with many learners pays very differently under each." } ], "picks": [ { "also": { "name": "Learnosity", "slug": "learnosity", "why": "C, 60.2/100" }, "name": "Moodle", "need": "Highest score overall", "slug": "moodle", "why": "B, 67.7/100 on the benchmark" }, { "name": "Instructure Canvas", "need": "Schema \u0026 documentation", "slug": "canvas-lms", "why": "77/100 on schema \u0026 documentation, against 66 for the overall leader" }, { "name": "Kahoot!", "need": "Agent ergonomics", "slug": "kahoot", "why": "66/100 on agent ergonomics, against 49 for the overall leader" }, { "name": "Kahoot!", "need": "Security \u0026 auth", "slug": "kahoot", "why": "69/100 on security \u0026 auth, against 67 for the overall leader" }, { "name": "Learnosity", "need": "Maintenance \u0026 community", "slug": "learnosity", "why": "85/100 on maintenance \u0026 community, against 81 for the overall leader" }, { "name": "Instructure Canvas", "need": "Transparency \u0026 trust", "slug": "canvas-lms", "why": "82/100 on transparency \u0026 trust, against 76 for the overall leader" }, { "name": "Learnosity", "need": "A hosted MCP endpoint", "slug": "learnosity", "why": "remote MCP server, nothing to install" } ], "ranked": 6, "shortlist": [ { "bestFor": "An agent working inside an institution or company that runs Moodle and can get a scoped token, reading course content, quiz attempts, assignments and grades or writing grades and enrolments.", "grade": "B", "name": "Moodle", "position": 1, "price": "Free · OSS", "score": 67.7, "slug": "moodle", "strengths": [ "About 800 to 900 external functions with typed, described parameters and returns, generated into a reference on every site", "Moodle 5.3 adds personal access tokens with scopes and 7-day to 1-year expiry, OAuth 2 clients and a SwaggerUI for the new REST API", "Services can expose only chosen functions to authorised users, with IP restriction and expiry on tokens" ], "url": "https://www.anchorterminal.com/tools/moodle", "verdict": "Free GPL software with about 800 typed web service functions over courses, quizzes, assignments and grades, a six-monthly release train with dated security advisories, and in 5.3 a scoped REST API with expiring tokens. An administrator must enable the services and issue tokens, the classic token travels in the query string, and no public OpenAPI file exists without a site.", "weaknesses": [ "A site administrator has to enable web services, build a service and issue a token before any call; nothing is self-serve", "The classic token goes in the `wstoken` query or POST parameter, is all-powerful within the user's capabilities and has no scopes", "No public OpenAPI or llms.txt; the machine-readable reference exists only inside a running site" ], "where": "hosted", "x402": "no" }, { "bestFor": "A product team embedding assessment at scale, where an agent imports items, reads sessions and scores, or runs reports under an existing contract.", "grade": "C", "name": "Learnosity", "position": 2, "price": "Paid", "score": 60.2, "slug": "learnosity", "strengths": [ "Data API covers item banks, learner sessions, responses, scores, scoring jobs and reports, with import and export endpoints", "Rate limits published per endpoint in 5-second windows, a 429 with meta.code 42000 and a stated wait", "LTS versions every February, June and October with 24 months of support and dated end-of-life and sunset tables" ], "url": "https://www.anchorterminal.com/tools/learnosity", "verdict": "A commercial assessment platform whose Data API reads and writes item banks, learner sessions and scores through signed requests, with published per-endpoint rate limits, dated LTS versions and a free hosted MCP server for its documentation. Access needs an annual per-user contract with no public price, no public OpenAPI document was found, and the subprocessor list is unreadable to crawlers.", "weaknesses": [ "Access needs a commercial agreement; no price, trial or self-serve key is published", "No public OpenAPI document or llms.txt was found; the reference is help-centre articles behind a Cloudflare challenge for crawlers", "Every call must be signed with the consumer secret, so an agent needs the SDK or the signing routine, and no read-only key type was found" ], "where": "hosted", "x402": "no" }, { "bestFor": "An agent acting for a teacher, student or administrator inside an institution that has issued a key, reading assignments and grades or creating course content.", "grade": "C", "name": "Instructure Canvas", "position": 3, "price": "Paid", "score": 59.5, "slug": "canvas-lms", "strengths": [ "REST API over courses, modules, assignments, quizzes, submissions, grades and users, plus a GraphQL endpoint with a GraphiQL explorer", "Developer keys scoped to `url:\u003cverb\u003e|\u003cpath\u003e` endpoints, 1-hour access tokens with refresh, and keys controlled by the institution's administrators", "API policy requires 90 days' notice before removing an endpoint or field, with a change log dated by announcement" ], "url": "https://www.anchorterminal.com/tools/canvas-lms", "verdict": "A wide REST and GraphQL API over an institution's courses, assignments, quizzes, submissions and grades, with scoped OAuth2 developer keys, Link-header paging, a 90-day deprecation policy and a dated change log. Access depends on an institution's administrator issuing a key, there is no public price or sandbox, and the API policy bars unapproved MCP connections.", "weaknesses": [ "An agent needs a developer key or OAuth grant from the institution's root administrator; Canvas Lite's terms exclude API token access", "No public price, trial or sandbox for the API, and the 2026 API policy forbids connecting through MCP servers Instructure has not approved", "Throttling is cost-based with no published quota, 429s carry no Retry-After, and no idempotency keys are documented for writes" ], "where": "hosted", "x402": "no" }, { "bestFor": "An agent shortlisting language tutors by price, rating and availability for a person to book.", "grade": "C", "name": "Preply", "position": 4, "price": "Free", "score": 57.4, "slug": "preply", "strengths": [ "Public OpenAPI 3.0.1 file and plugin manifest at preply.com, with typed filters and enums for sort, availability day and time", "No key, signup or card for the search API; results carry each tutor's hourly price, rating, lesson count and public URL", "Status page at status.preply.com with five components and dated incident archives; none since 2 June 2026" ], "url": "https://www.anchorterminal.com/tools/preply", "verdict": "Two keyless GET endpoints, described in a public OpenAPI file with enums for sort, day and time, let an agent search tutors by subject and price and read a profile. Nothing books, pays or messages, the endpoints sit under a path robots.txt disallows, the terms forbid automated access without written authorisation, and no rate limits or errors are documented.", "weaknesses": [ "No API for booking, messaging, lessons or payment; the tutor search is the whole surface, and the subject enum lists only english, spanish and ukrainian", "The endpoints live under /api/, which preply.com/robots.txt disallows for every crawler, so we could not confirm they still answer", "The terms forbid automated access by scripts, bots or scrapers without a separate written agreement, while the manifest invites agents in with no auth" ], "where": "local", "x402": "no" }, { "bestFor": "An enterprise's own agents pulling session results, participants and answers into BI or an LMS.", "grade": "C", "name": "Kahoot!", "position": 5, "price": "$9 / seat-mo", "score": 55.2, "slug": "kahoot", "strengths": [ "Public OpenAPI 3.1.0 file at results.kahoot.com/openapi with typed schemas for every answer type, cursor pagination and a limit of 1 to 100", "Every endpoint is a GET, so an agent reading sessions and answers can retry safely and cannot change anything", "Atlassian Statuspage with component history; one minor incident in the 90 days to 3 November 2026" ], "url": "https://www.anchorterminal.com/tools/kahoot", "verdict": "A public OpenAPI file describes a read-only Data API of 11 endpoints with cursor pagination and OAuth 2.0 client credentials, backed by a status page and ISO 27001. Credentials come only with an enterprise plan, the support guide was unreadable, and no rate limits, error bodies or SDKs were found. An agent cannot create or run a kahoot.", "weaknesses": [ "API credentials are issued by Kahoot! to organisations on an enterprise plan priced by quote; no self-serve key, trial or free tier for the API", "No rate limits, 429 handling, error response bodies or SLA found in the OpenAPI file or the pages we could read", "The support guide to the reports API answered our reader with a Cloudflare check, so the request process and data window weren't read first-hand" ], "where": "local", "x402": "no" }, { "bestFor": "An agent that has to turn a person's own material into a quiz, flashcards and notes in one call and can wait for generation.", "grade": "F", "name": "Quizgecko", "position": 6, "price": "$16 / mo", "score": 33, "slug": "quizgecko", "strengths": [ "Public OpenAPI 3.1.0 document and an RFC 9727 API catalogue at /.well-known, plus llms.txt", "One POST /generate call turns text, a URL, uploads or a topic into a course with quizzes, flashcards and study notes, with language, difficulty and question-type options", "A generation-status endpoint reports progress and per-module readiness so an agent can poll instead of guessing" ], "url": "https://www.anchorterminal.com/tools/quizgecko", "verdict": "A small OpenAPI 3.1 surface generates a course of quizzes, flashcards and notes from text, a URL or an upload and polls it to completion. API access is granted on request with no published price or rate limit, one bearer token that may travel in the query string, and the terms, privacy policy and security page could not be read.", "weaknesses": [ "API access is by contacting Quizgecko, with no published API price, rate limit, SLA or status page", "One bearer token with no scopes, and `?api_key=` in the query string is a documented option", "The question endpoints and file upload are documented in HTML but missing from the OpenAPI document, and the PUT /quizzes body is an untyped object" ], "where": "hosted", "x402": "no" } ], "updated": "2026-11-03" }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/best/learning/", "json": "https://www.anchorterminal.com/best/learning/index.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/best/learning/index.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/best/learning/index.min.md" }, "markdown": "All 6 ranked learning, tutoring and assessment tools on the Anchor benchmark, with a pick for each need and where each one falls short. Scores come from public evidence, re-checked as vendors change.\n\n- Ranked: 6 · agent-ready (BB or better): 0 · accept x402: 0 · hosted endpoints: 4\n- Full ranked table: https://www.anchorterminal.com/categories/learning.md\n- Head-to-head comparisons: https://www.anchorterminal.com/compare/learning/index.md (10)\n- Methodology: https://www.anchorterminal.com/benchmark/index.md\n\n## The shortlist\n\n| # | Tool | Grade | Score | Best for | Price | Where |\n| --- | --- | --- | --- | --- | --- | --- |\n| 1 | [Moodle](https://www.anchorterminal.com/tools/moodle.md) | B | 67.7 | An agent working inside an institution or company that runs Moodle and can get a scoped token, reading course content, quiz attempts, assignments and grades or writing grades and enrolments. | Free · OSS | Hosted |\n| 2 | [Learnosity](https://www.anchorterminal.com/tools/learnosity.md) | C | 60.2 | A product team embedding assessment at scale, where an agent imports items, reads sessions and scores, or runs reports under an existing contract. | Paid | Hosted |\n| 3 | [Instructure Canvas](https://www.anchorterminal.com/tools/canvas-lms.md) | C | 59.5 | An agent acting for a teacher, student or administrator inside an institution that has issued a key, reading assignments and grades or creating course content. | Paid | Hosted |\n| 4 | [Preply](https://www.anchorterminal.com/tools/preply.md) | C | 57.4 | An agent shortlisting language tutors by price, rating and availability for a person to book. | Free | Local |\n| 5 | [Kahoot!](https://www.anchorterminal.com/tools/kahoot.md) | C | 55.2 | An enterprise's own agents pulling session results, participants and answers into BI or an LMS. | $9 / seat-mo | Local |\n| 6 | [Quizgecko](https://www.anchorterminal.com/tools/quizgecko.md) | F | 33 | An agent that has to turn a person's own material into a quiz, flashcards and notes in one call and can wait for generation. | $16 / mo | Hosted |\n\n## Picks by need\n\n- Highest score overall: [Moodle](https://www.anchorterminal.com/tools/moodle.md), B, 67.7/100 on the benchmark. Also [Learnosity](https://www.anchorterminal.com/tools/learnosity.md), C, 60.2/100.\n- Schema \u0026 documentation: [Instructure Canvas](https://www.anchorterminal.com/tools/canvas-lms.md), 77/100 on schema \u0026 documentation, against 66 for the overall leader.\n- Agent ergonomics: [Kahoot!](https://www.anchorterminal.com/tools/kahoot.md), 66/100 on agent ergonomics, against 49 for the overall leader.\n- Security \u0026 auth: [Kahoot!](https://www.anchorterminal.com/tools/kahoot.md), 69/100 on security \u0026 auth, against 67 for the overall leader.\n- Maintenance \u0026 community: [Learnosity](https://www.anchorterminal.com/tools/learnosity.md), 85/100 on maintenance \u0026 community, against 81 for the overall leader.\n- Transparency \u0026 trust: [Instructure Canvas](https://www.anchorterminal.com/tools/canvas-lms.md), 82/100 on transparency \u0026 trust, against 76 for the overall leader.\n- A hosted MCP endpoint: [Learnosity](https://www.anchorterminal.com/tools/learnosity.md), remote MCP server, nothing to install.\n\n## How to choose\n\n- Create or read only: Check whether the API can make a quiz or a card set from text or only returns what people made in the app, since an agent that cannot create has nothing to hand a learner.\n- Learner data and consent: Check what the API returns about a learner and who has to consent, because school and child data carry rules the agent's operator answers for.\n- Institution approval: Check whether a school or an administrator has to switch access on, as a course system often keeps its API behind an institution's own keys.\n- Price per learner: Check whether the price is per learner, per seat or per item made, since a tutoring agent with many learners pays very differently under each.\n\n- How the benchmark tests this category: In this run, public evidence against the published checklist. When the task suites run, the same chapter turned into a ten-question quiz and a flashcard set through each listing, a learner's answers recorded and the score read back. We check the questions against the text, what the API says about the learner and what a school account has to allow.\n\n## Each one in detail\n\n### 1. Moodle, B 67.7/100\n\nMoodle is an open-source learning management system that schools and companies run themselves or through MoodleCloud. Its web services expose 800 functions for courses, quizzes, assignments and grades, and Moodle 5.3 adds a scoped REST API with personal access tokens.\n\n- Verdict: Free GPL software with about 800 typed web service functions over courses, quizzes, assignments and grades, a six-monthly release train with dated security advisories, and in 5.3 a scoped REST API with expiring tokens. An administrator must enable the services and issue tokens, the classic token travels in the query string, and no public OpenAPI file exists without a site.\n- Best for: An agent working inside an institution or company that runs Moodle and can get a scoped token, reading course content, quiz attempts, assignments and grades or writing grades and enrolments.\n- Strength: About 800 to 900 external functions with typed, described parameters and returns, generated into a reference on every site\n- Strength: Moodle 5.3 adds personal access tokens with scopes and 7-day to 1-year expiry, OAuth 2 clients and a SwaggerUI for the new REST API\n- Strength: Services can expose only chosen functions to authorised users, with IP restriction and expiry on tokens\n- Weakness: A site administrator has to enable web services, build a service and issue a token before any call; nothing is self-serve\n- Weakness: The classic token goes in the `wstoken` query or POST parameter, is all-powerful within the user's capabilities and has no scopes\n- Weakness: No public OpenAPI or llms.txt; the machine-readable reference exists only inside a running site\n- Price: Free · OSS · Auth: OAuth or key · x402: No · Where: Hosted\n- Full assessment: https://www.anchorterminal.com/tools/moodle.md\n\n### 2. Learnosity, C 60.2/100\n\nLearnosity is an assessment platform that education companies embed in their products. Its Data API imports item banks and reads learner sessions, responses and scores, with browser APIs for authoring and delivery and a hosted MCP server for its documentation.\n\n- Verdict: A commercial assessment platform whose Data API reads and writes item banks, learner sessions and scores through signed requests, with published per-endpoint rate limits, dated LTS versions and a free hosted MCP server for its documentation. Access needs an annual per-user contract with no public price, no public OpenAPI document was found, and the subprocessor list is unreadable to crawlers.\n- Best for: A product team embedding assessment at scale, where an agent imports items, reads sessions and scores, or runs reports under an existing contract.\n- Strength: Data API covers item banks, learner sessions, responses, scores, scoring jobs and reports, with import and export endpoints\n- Strength: Rate limits published per endpoint in 5-second windows, a 429 with meta.code 42000 and a stated wait\n- Strength: LTS versions every February, June and October with 24 months of support and dated end-of-life and sunset tables\n- Weakness: Access needs a commercial agreement; no price, trial or self-serve key is published\n- Weakness: No public OpenAPI document or llms.txt was found; the reference is help-centre articles behind a Cloudflare challenge for crawlers\n- Weakness: Every call must be signed with the consumer secret, so an agent needs the SDK or the signing routine, and no read-only key type was found\n- Price: Paid · Auth: API key · x402: No · Where: Hosted\n- Full assessment: https://www.anchorterminal.com/tools/learnosity.md\n- Against #1: https://www.anchorterminal.com/compare/learnosity-vs-moodle.md\n\n### 3. Instructure Canvas, C 59.5/100\n\nCanvas is Instructure's learning management system for schools and universities. Its REST and GraphQL APIs read and change courses, assignments, quizzes, submissions and grades on an institution's Canvas domain, with OAuth2 developer keys its administrators issue and scope.\n\n- Verdict: A wide REST and GraphQL API over an institution's courses, assignments, quizzes, submissions and grades, with scoped OAuth2 developer keys, Link-header paging, a 90-day deprecation policy and a dated change log. Access depends on an institution's administrator issuing a key, there is no public price or sandbox, and the API policy bars unapproved MCP connections.\n- Best for: An agent acting for a teacher, student or administrator inside an institution that has issued a key, reading assignments and grades or creating course content.\n- Strength: REST API over courses, modules, assignments, quizzes, submissions, grades and users, plus a GraphQL endpoint with a GraphiQL explorer\n- Strength: Developer keys scoped to `url:\u003cverb\u003e|\u003cpath\u003e` endpoints, 1-hour access tokens with refresh, and keys controlled by the institution's administrators\n- Strength: API policy requires 90 days' notice before removing an endpoint or field, with a change log dated by announcement\n- Weakness: An agent needs a developer key or OAuth grant from the institution's root administrator; Canvas Lite's terms exclude API token access\n- Weakness: No public price, trial or sandbox for the API, and the 2026 API policy forbids connecting through MCP servers Instructure has not approved\n- Weakness: Throttling is cost-based with no published quota, 429s carry no Retry-After, and no idempotency keys are documented for writes\n- Price: Paid · Auth: OAuth · x402: No · Where: Hosted\n- Full assessment: https://www.anchorterminal.com/tools/canvas-lms.md\n- Against #1: https://www.anchorterminal.com/compare/canvas-lms-vs-moodle.md\n\n### 4. Preply, C 57.4/100\n\nPreply is a marketplace for one-to-one language lessons with tutors who set their own hourly prices. A small keyless tutor-search API, published as a plugin manifest with an OpenAPI file, returns tutor listings and profiles; booking stays in the app.\n\n- Verdict: Two keyless GET endpoints, described in a public OpenAPI file with enums for sort, day and time, let an agent search tutors by subject and price and read a profile. Nothing books, pays or messages, the endpoints sit under a path robots.txt disallows, the terms forbid automated access without written authorisation, and no rate limits or errors are documented.\n- Best for: An agent shortlisting language tutors by price, rating and availability for a person to book.\n- Strength: Public OpenAPI 3.0.1 file and plugin manifest at preply.com, with typed filters and enums for sort, availability day and time\n- Strength: No key, signup or card for the search API; results carry each tutor's hourly price, rating, lesson count and public URL\n- Strength: Status page at status.preply.com with five components and dated incident archives; none since 2 June 2026\n- Weakness: No API for booking, messaging, lessons or payment; the tutor search is the whole surface, and the subject enum lists only english, spanish and ukrainian\n- Weakness: The endpoints live under /api/, which preply.com/robots.txt disallows for every crawler, so we could not confirm they still answer\n- Weakness: The terms forbid automated access by scripts, bots or scrapers without a separate written agreement, while the manifest invites agents in with no auth\n- Price: Free · Auth: None · x402: No · Where: Local\n- Full assessment: https://www.anchorterminal.com/tools/preply.md\n\n### 5. Kahoot!, C 55.2/100\n\nKahoot! is a quiz and presentation platform for schools and workplaces. Its Kahoot Data API, a read-only REST API for enterprise organisations, returns users, kahoots, game sessions, participants and answers under OAuth 2.0 client credentials from Kahoot!.\n\n- Verdict: A public OpenAPI file describes a read-only Data API of 11 endpoints with cursor pagination and OAuth 2.0 client credentials, backed by a status page and ISO 27001. Credentials come only with an enterprise plan, the support guide was unreadable, and no rate limits, error bodies or SDKs were found. An agent cannot create or run a kahoot.\n- Best for: An enterprise's own agents pulling session results, participants and answers into BI or an LMS.\n- Strength: Public OpenAPI 3.1.0 file at results.kahoot.com/openapi with typed schemas for every answer type, cursor pagination and a limit of 1 to 100\n- Strength: Every endpoint is a GET, so an agent reading sessions and answers can retry safely and cannot change anything\n- Strength: Atlassian Statuspage with component history; one minor incident in the 90 days to 3 November 2026\n- Weakness: API credentials are issued by Kahoot! to organisations on an enterprise plan priced by quote; no self-serve key, trial or free tier for the API\n- Weakness: No rate limits, 429 handling, error response bodies or SLA found in the OpenAPI file or the pages we could read\n- Weakness: The support guide to the reports API answered our reader with a Cloudflare check, so the request process and data window weren't read first-hand\n- Price: $9 / seat-mo · Auth: OAuth · x402: No · Where: Local\n- Full assessment: https://www.anchorterminal.com/tools/kahoot.md\n- Against #1: https://www.anchorterminal.com/compare/kahoot-vs-moodle.md\n\n### 6. Quizgecko, F 33/100\n\nQuizgecko is a study app from Version Zero Limited that turns notes, documents, links and recordings into quizzes, flashcards, notes and podcasts. Its V2 API generates a course from text, a URL, uploads or a topic and edits the quizzes.\n\n- Verdict: A small OpenAPI 3.1 surface generates a course of quizzes, flashcards and notes from text, a URL or an upload and polls it to completion. API access is granted on request with no published price or rate limit, one bearer token that may travel in the query string, and the terms, privacy policy and security page could not be read.\n- Best for: An agent that has to turn a person's own material into a quiz, flashcards and notes in one call and can wait for generation.\n- Strength: Public OpenAPI 3.1.0 document and an RFC 9727 API catalogue at /.well-known, plus llms.txt\n- Strength: One POST /generate call turns text, a URL, uploads or a topic into a course with quizzes, flashcards and study notes, with language, difficulty and question-type options\n- Strength: A generation-status endpoint reports progress and per-module readiness so an agent can poll instead of guessing\n- Weakness: API access is by contacting Quizgecko, with no published API price, rate limit, SLA or status page\n- Weakness: One bearer token with no scopes, and `?api_key=` in the query string is a documented option\n- Weakness: The question endpoints and file upload are documented in HTML but missing from the OpenAPI document, and the PUT /quizzes body is an untyped object\n- Price: $16 / mo · Auth: API key · x402: No · Where: Hosted\n- Full assessment: https://www.anchorterminal.com/tools/quizgecko.md\n- Against #1: https://www.anchorterminal.com/compare/moodle-vs-quizgecko.md\n\n## Head to head\n\n- [Learnosity vs Moodle](https://www.anchorterminal.com/compare/learnosity-vs-moodle.md)\n- [Instructure Canvas vs Moodle](https://www.anchorterminal.com/compare/canvas-lms-vs-moodle.md)\n- [Kahoot! vs Moodle](https://www.anchorterminal.com/compare/kahoot-vs-moodle.md)\n- [Instructure Canvas vs Learnosity](https://www.anchorterminal.com/compare/canvas-lms-vs-learnosity.md)\n- [Kahoot! vs Learnosity](https://www.anchorterminal.com/compare/kahoot-vs-learnosity.md)\n- [Instructure Canvas vs Kahoot!](https://www.anchorterminal.com/compare/canvas-lms-vs-kahoot.md)\n\n## Questions\n\n### What are the highest-rated learning, tutoring and assessment tools for AI agents?\n\nMoodle has the highest benchmark score of the 6 ranked learning, tutoring and assessment tools, 67.7 (B). Learnosity is second with 60.2 (C).\n\n### How many learning, tutoring and assessment tools are agent-ready?\n\n0 of the 6 ranked here grade BB or better, the bar for agent-ready on the Anchor benchmark.\n\n### Which learning, tutoring and assessment tools accept x402 payments?\n\nNone of the ranked listings here accepts x402 for its main call yet.\n\n### How is this list ranked?\n\nBy the Anchor benchmark score out of 100, a weighted mean of the scored categories minus deductions for negative events, from public evidence re-checked as vendors change. Listings cannot pay for a place. The latest assessment behind this page is from 3 November 2026.\n\n## How this list is made\n\nThe order is the Anchor benchmark score, the same number as on each listing. Each listing is graded from public evidence against the benchmark checklist, and the picks are worked out from those grades, prices and facts. No listing pays for its place, and paid audits or listing help never change a score.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-04", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Best of", "url": "https://www.anchorterminal.com/best/" }, { "name": "Learning, tutoring \u0026 assessment", "url": "" } ], "description": "Moodle (B), Learnosity (C) and Instructure Canvas (C) lead the 6 ranked learning, tutoring and assessment tools. Picks by need, strengths, weaknesses and prices from the Anchor benchmark.", "facts": [ "Moodle B", "Learnosity C", "Instructure Canvas C" ], "h1": "Best learning, tutoring and assessment tools for AI agents", "image": "https://www.anchorterminal.com/assets/og/best-learning.png", "path": "/best/learning/", "published": "", "section": "tools", "title": "Best learning, tutoring and assessment tools for AI agents in 2026", "toc": null, "updated": "2026-11-03", "url": "https://www.anchorterminal.com/best/learning/" }, "tokens": { "markdown": 4400, "slim": 1180 }, "version": 1 }