{"category":{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","tagline":null,"description":null,"synonyms":[],"target_queries":[],"added_via":"pr","added_at":"2026-09-05T04:05:21.110Z","updated_at":"2026-09-05T04:05:21.110Z","example":false,"profile_url":"/categories/benchmarks","is_stub":true,"member_count":5,"member_counts":{"product":5}},"members":[{"listing_type":"product","name":"knowAIedge","slug":"knowaiedge","tagline":"Source-linked AI news, model benchmarks, and GitHub repository discovery","description":"knowAIedge is an AI knowledge hub bringing together source-linked AI news and articles, model benchmark comparisons, GitHub repository discovery, and a video watchlist. Readers can explore coverage of AI tools, coding, robotics, research, and industry developments, with clear summaries and links to original sources.","url":"https://knowaiedge.fyi/","is_stealth":false,"normalized_domain":"knowaiedge.fyi","normalized_url_key":"knowaiedge.fyi","parent_slug":null,"parent":null,"type_data":{"product_kind":null,"pricing_model":null,"platforms":["web"],"free_tier":null,"open_source":null,"launched_year":null,"pricing_url":null,"docs_url":null,"changelog_url":null,"status_url":null,"use_cases":[],"integrations":[],"alternatives":[]},"logo":null,"links":[],"entry_points":[{"kind":"homepage","url":"https://knowaiedge.fyi/","audience":"any","primary":false,"listed_by":"community","derived_from":"url","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"homepage","url":"https://knowaiedge.fyi/","audience":"any","primary":false,"listed_by":"community","derived_from":"url","on_listing_domain":true},"agent":null},"founders":[],"media":null,"categories":["AI","News","Research","Benchmarks"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-11-03T06:12:06.362Z","added_via":"web","geo":null,"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-11-03T06:12:06.362Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","note":null,"profile_url":"/categories/benchmarks"},{"kind":"product_category","slug":"news","name":"News","note":null,"profile_url":"/categories/news"},{"kind":"product_category","slug":"research","name":"Research","note":null,"profile_url":"/categories/research"}],"membership":{"note":null,"source":"listing","added_via":"web","added_at":"2026-11-03T06:12:06.362Z","updated_at":"2026-11-03T06:12:06.362Z"}},{"listing_type":"product","name":"BabaBench","slug":"bababench","tagline":"Benchmark measuring how well frontier AI agents complete real long-horizon patient advocacy tasks","description":"BabaBench is Baba's research benchmark for AI agents on patient advocacy. It rebuilds real advocacy tasks, such as housing navigation, insurer calls, paperwork, billing and consent, as simulations that agents must work through end to end with patients, payers, providers and agencies, testing whether an agent can finish the job without privacy violations or prohibited actions. It is available as an arXiv preprint and was accepted to a NeurIPS workshop, per Baba.","url":"https://www.callbaba.com/bench/","is_stealth":false,"normalized_domain":"callbaba.com","normalized_url_key":"callbaba.com/bench","parent_slug":"baba","parent":{"slug":"baba","name":"Baba","listing_type":"company","profile_url":"/companies/baba"},"type_data":{"product_kind":"other"},"logo":"https://www.callbaba.com/apple-touch-icon.png","links":[],"entry_points":[{"kind":"homepage","url":"https://www.callbaba.com/bench/","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"homepage","url":"https://www.callbaba.com/bench/","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true},"agent":null},"founders":[],"media":{"logo_asset_id":"22c8cd41-7913-4948-9903-f857eb7b6c65"},"categories":["AI","Benchmarks","Healthcare"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-10-20T22:46:07.815Z","added_via":"web","geo":null,"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-10-20T22:46:26.988Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","note":null,"profile_url":"/categories/benchmarks"},{"kind":"product_category","slug":"healthcare","name":"Healthcare","note":null,"profile_url":"/categories/healthcare"}],"membership":{"note":null,"source":"listing","added_via":"web","added_at":"2026-10-20T22:46:07.815Z","updated_at":"2026-10-20T22:46:07.815Z"}},{"listing_type":"product","name":"Jarvis Bench","slug":"jarvis-bench","tagline":"Frontier evaluation suite for Voice AI agents","description":"Jarvis Bench is Voice Arena's frontier evaluation suite for voice AI agents, offered alongside the public TTS/STT leaderboards and Sales Agent Eval on voicearena.com.","url":"https://voicearena.com/jarvis-bench","is_stealth":false,"normalized_domain":"voicearena.com","normalized_url_key":"voicearena.com/jarvis-bench","parent_slug":"voice-arena","parent":{"slug":"voice-arena","name":"Voice Arena","listing_type":"company","profile_url":"/companies/voice-arena"},"type_data":{"product_kind":"saas","platforms":["web"],"use_cases":["Evaluate voice AI agents","Compare frontier voice agent capabilities"]},"logo":"https://voicearena.com/apple-touch-icon.png","links":[],"entry_points":[{"kind":"homepage","url":"https://voicearena.com/jarvis-bench","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"homepage","url":"https://voicearena.com/jarvis-bench","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true},"agent":null},"founders":[],"media":{"logo_asset_id":"da6b25ab-f2b0-4a5a-849d-fa6779667f7e"},"categories":["Voice AI","Benchmarks","AI Agents"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-10-04T19:26:15.815Z","added_via":"web","geo":null,"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-10-04T19:26:15.815Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai-agents","name":"AI Agents","note":null,"profile_url":"/categories/ai-agents"},{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","note":null,"profile_url":"/categories/benchmarks"},{"kind":"product_category","slug":"voice-ai","name":"Voice AI","note":null,"profile_url":"/categories/voice-ai"}],"membership":{"note":null,"source":"listing","added_via":"web","added_at":"2026-10-04T19:26:15.815Z","updated_at":"2026-10-04T19:26:15.815Z"}},{"listing_type":"product","name":"Voice Arena TTS Leaderboard","slug":"voice-arena-tts","tagline":"Public text-to-speech quality and latency leaderboard from real production calls","description":"Voice Arena's TTS Leaderboard ranks text-to-speech models on Bradley-Terry Elo quality and time-to-first-audio using datasets built from real production calls across languages and industry categories. Creators can add models and review arena methodology on voicearena.com.","url":"https://voicearena.com/","is_stealth":false,"normalized_domain":"voicearena.com","normalized_url_key":"voicearena.com","parent_slug":"voice-arena","parent":{"slug":"voice-arena","name":"Voice Arena","listing_type":"company","profile_url":"/companies/voice-arena"},"type_data":{"product_kind":"saas","platforms":["web"],"use_cases":["Compare TTS models on quality and latency","Benchmark voice AI for production call workloads"]},"logo":"https://voicearena.com/apple-touch-icon.png","links":[{"label":"LinkedIn","url":"https://www.linkedin.com/company/voice-arena","platform":"linkedin"}],"entry_points":[{"kind":"homepage","url":"https://voicearena.com/","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"homepage","url":"https://voicearena.com/","audience":"human","primary":true,"listed_by":"community","on_listing_domain":true},"agent":null},"founders":[],"media":{"logo_asset_id":"ab18611f-99cd-4acc-ad72-9e363b587283"},"categories":["Voice AI","Benchmarks","AI"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":"https://www.linkedin.com/company/voice-arena","contact_email":null,"added_at":"2026-10-04T19:26:08.430Z","added_via":"web","geo":null,"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-10-04T19:26:08.430Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","note":null,"profile_url":"/categories/benchmarks"},{"kind":"product_category","slug":"voice-ai","name":"Voice AI","note":null,"profile_url":"/categories/voice-ai"}],"membership":{"note":null,"source":"listing","added_via":"web","added_at":"2026-10-04T19:26:08.430Z","updated_at":"2026-10-04T19:26:08.430Z"}},{"listing_type":"product","name":"ARC-AGI Benchmark Series","slug":"arc-agi-benchmark-series","tagline":"Open-source AI benchmarks that measure general fluid intelligence and guide AGI research.","description":"The ARC Prize Foundation publishes the ARC-AGI benchmark series—scientifically grounded evaluations designed to reveal the gap between tasks that are easy for humans but hard for AI. The series includes ARC-AGI-3, described as the world's only unbeaten benchmark measuring agentic intelligence. The benchmarks are used by OpenAI, Anthropic, Google DeepMind, and xAI, and are recognized by NIST's Center for AI Standards and Innovation. Competitions run in partnership with Kaggle, offering over $2M in prizes for open-sourced progress on the benchmarks.\n\nARC-AGI Benchmark Series is a product of ARC Prize Foundation.","url":"https://arcprize.org/","is_stealth":false,"normalized_domain":"arcprize.org","normalized_url_key":"arcprize.org","parent_slug":"arc-prize-foundation","parent":{"slug":"arc-prize-foundation","name":"ARC Prize Foundation","listing_type":"company","profile_url":"/companies/arc-prize-foundation"},"type_data":{"product_kind":"open_source","pricing_model":"free","platforms":["web"],"free_tier":true,"open_source":true,"use_cases":["Evaluate AI systems for general fluid intelligence","Identify inflection points in AI progress","Guide open AGI research","Regulatory standards for AI capability measurement","Compete for prize funding via Kaggle"],"integrations":["Kaggle"]},"logo":null,"links":[],"entry_points":[{"kind":"signup","url":"https://arcprize.org/","audience":"human","primary":false,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"signup","url":"https://arcprize.org/","audience":"human","primary":false,"listed_by":"community","on_listing_domain":true},"agent":null},"founders":[],"media":null,"categories":["AI","Research","Open Source","Benchmarks","Industrials"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-09-05T04:05:21.110Z","added_via":"web","geo":{"keywords":["ARC-AGI Benchmark Series","ARC Prize Foundation","AI","Research","Open Source","Benchmarks","Industrials"],"canonical_facts":["Product of ARC Prize Foundation"]},"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-09-05T04:05:21.110Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"kind":"product_category","slug":"benchmarks","name":"Benchmarks","note":null,"profile_url":"/categories/benchmarks"},{"kind":"product_category","slug":"industrials","name":"Industrials","note":null,"profile_url":"/categories/industrials"},{"kind":"product_category","slug":"open-source","name":"Open Source","note":null,"profile_url":"/categories/open-source"},{"kind":"product_category","slug":"research","name":"Research","note":null,"profile_url":"/categories/research"}],"membership":{"note":null,"source":"listing","added_via":"web","added_at":"2026-09-05T04:05:21.110Z","updated_at":"2026-09-05T04:05:21.110Z"}}],"total":5,"limit":50,"offset":0}