{"url":"https://etfiq.com/research/ai-accuracy/","section":"research","title":"AI Accuracy Benchmark: askIQ vs 8 AI Models on ETF Numbers | ETFIQ","description":"askIQ (ETFIQ) answered 99% of 100 ETF questions dated Oct 29, 2026 correctly. Every number scored against ETFIQ data.","as_of":"Oct 29, 2026","structured_data":[{"@type":"Dataset","@id":"https://etfiq.com/research/ai-accuracy/#dataset","name":"ETFIQ AI accuracy benchmark, Oct 29, 2026","description":"askIQ (ETFIQ) answered 99% of 100 ETF questions dated Oct 29, 2026 correctly. Every number scored against ETFIQ data.","url":"https://etfiq.com/research/ai-accuracy/","dateModified":"2026-10-29","temporalCoverage":"2026-10-29","creator":{"@id":"https://etfiq.com/#org"},"publisher":{"@id":"https://etfiq.com/#org"},"isAccessibleForFree":true,"license":"https://etfiq.com/license/","measurementTechnique":"Numbers in each answer matched on quantity against ETFIQ published data","distribution":[{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/questions.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/askiq.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/openai-gpt-6-astra-web.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/gemini-4-argon-search.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/perplexity-sonar.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/openai-gpt-6-astra.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/claude-opus-5-5.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/gemini-4-argon.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/claude-haiku-5-5.json"},{"@type":"DataDownload","encodingFormat":"application/json","contentUrl":"https://etfiq.com/data/ai-accuracy/2026-10-29/runs/claude-sonnet-5-5.json"}],"inLanguage":"en","creativeWorkStatus":"Published"},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"ETFIQ","item":"https://etfiq.com/"},{"@type":"ListItem","position":2,"name":"Research","item":"https://etfiq.com/research/"},{"@type":"ListItem","position":3,"name":"AI accuracy benchmark","item":"https://etfiq.com/research/ai-accuracy/"}]},{"@type":"WebPage","name":"AI Accuracy Benchmark: askIQ vs 8 AI Models on ETF Numbers","description":"askIQ (ETFIQ) answered 99% of 100 ETF questions dated Oct 29, 2026 correctly. Every number scored against ETFIQ data.","url":"https://etfiq.com/research/ai-accuracy/","dateModified":"2026-10-29","isPartOf":{"@type":"WebSite","name":"ETFIQ","url":"https://etfiq.com"},"speakable":{"@type":"SpeakableSpecification","cssSelector":[".lede"]},"publisher":{"@id":"https://etfiq.com/#org"}}],"characters":17200,"truncated":false,"content":"ETFIQ / Research / AI accuracy benchmark \n \n AI accuracy benchmark, questions dated Oct 29, 2026.\n AI accuracy benchmark: do assistants get ETF numbers right?\n On 100 ETF questions dated Oct 29, 2026, askIQ (ETFIQ) answered 99% correctly; GPT-6 Astra + web search answered 92%.\n \n 100 questions \n 9 systems measured \n 493 answers that gave a number \n\n Scores\n Scores on the questions dated Oct 29, 2026 System Answers correct Right when it gave a number Refused \n askIQ (ETFIQ) 99% of 100 ( 95% to 100% ) 100% of 99 ( 96% to 100% ) 1 \n GPT-6 Astra + web search 92% of 100 ( 85% to 96% ) 93% of 99 ( 86% to 97% ) 0 \n Gemini 4 Argon + Google Search 78% of 100 ( 69% to 85% ) 78% of 100 ( 69% to 85% ) 0 \n Perplexity Sonar 75% of 100 ( 66% to 82% ) 80% of 94 ( 71% to 87% ) 6 \n GPT-6 Astra 26% of 100 ( 18% to 35% ) 90% of 29 ( 74% to 96% ) 71 \n Claude Opus 5.5 22% of 100 ( 15% to 31% ) 92% of 24 ( 74% to 98% ) 76 \n Gemini 4 Argon 17% of 100 ( 11% to 26% ) 100% of 17 ( 82% to 100% ) 83 \n Claude Haiku 5.5 16% of 100 ( 10% to 24% ) 89% of 18 ( 67% to 97% ) 82 \n Claude Sonnet 5.5 12% of 100 ( 7% to 20% ) 92% of 13 ( 67% to 99% ) 87 \n Systems\n askIQ (ETFIQ): model claude-sonnet-5-5, answered Oct 30, 2026, run cost $1.89\n GPT-6 Astra + web search: model gpt-6-astra, answered Oct 30, 2026, run cost $22.79\n Gemini 4 Argon + Google Search: model gemini-4-argon, answered Oct 30, 2026, run cost $2.91\n Perplexity Sonar: model sonar (Agent API effort fast), answered Oct 30, 2026, run cost $0.21\n GPT-6 Astra: model gpt-6-astra, answered Oct 30, 2026, run cost $1.05\n Claude Opus 5.5: model claude-opus-5-5, answered Oct 30, 2026, run cost $0.91\n Gemini 4 Argon: model gemini-4-argon, answered Oct 30, 2026, run cost $0.12\n Claude Haiku 5.5: model claude-haiku-5-5, answered Oct 30, 2026, run cost $0.02\n Claude Sonnet 5.5: model claude-sonnet-5-5, answered Oct 30, 2026, run cost $0.31\n Questions and answers\n Every question: the ETFIQ answer and each system's claim (\u2713 right, \u2717 wrong) Question ETFIQ data askIQ (ETFIQ) GPT-6 Astra + web search Gemini 4 Argon + Google Search Perplexity Sonar GPT-6 Astra Claude Opus 5.5 Gemini 4 Argon Claude Haiku 5.5 Claude Sonnet 5.5 \n ALTY 1-year total return, Oct 29, 2026 6.766% 6.8% \u2713 6.7% \u2713 5.83% \u2717 6.7% \u2713 Refused Refused Refused Refused Refused \n GMOD 1-year total return, Oct 29, 2026 11.79% 11.8% \u2713 11.78% \u2713 10.94% \u2717 Refused Refused Refused Refused Refused Refused \n CAOS 1-year total return, Oct 29, 2026 1.523% 1.5% \u2713 1.52% \u2713 1.36% \u2717 1.52% \u2713 Refused Refused Refused Refused Refused \n DBMF 1-year total return, Oct 29, 2026 21.63% 21.6% \u2713 21.64% \u2713 21.63% \u2713 21.8% \u2717 Refused Refused Refused Refused Refused \n FCOR 1-year total return, Oct 29, 2026 \u22121.703% \u22121.7% \u2713 \u22122.89% \u2717 \u22122.25% \u2717 \u22121.7% \u2713 Refused Refused Refused Refused Refused \n FEMB 1-year total return, Oct 29, 2026 2.326% 2.3% \u2713 2.33% \u2713 2.2% \u2713 2.3% \u2713 Refused Refused Refused Refused Refused \n IMAR 1-year total return, Oct 29, 2026 4.669% 4.7% \u2713 4.6% \u2713 4.65% \u2713 4.35% \u2717 Refused Refused Refused Refused Refused \n NJUN 1-year total return, Oct 29, 2026 5.186% 5.2% \u2713 5.19% \u2713 5.14% \u2713 6% \u2717 Refused Refused Refused Refused Refused \n BWET 1-year total return, Oct 29, 2026 5106% 5106% \u2713 5106% \u2713 5105% \u2717 5120% \u2717 Refused Refused Refused Refused Refused \n CMDY 1-year total return, Oct 29, 2026 34.44% 34.4% \u2713 34.44% \u2713 34.27% \u2717 Refused Refused Refused Refused Refused Refused \n DOJE 1-year total return, Oct 29, 2026 \u221259.67% \u221259.7% \u2713 \u221259.67% \u2713 \u221260.3% \u2717 \u221259.8% \u2713 Refused Refused Refused Refused Refused \n AIYY 1-year total return, Oct 29, 2026 \u221240% \u221240% \u2713 \u221240.84% \u2717 \u221239.85% \u2717 \u221241.46% \u2717 Refused Refused Refused Refused Refused \n BOEU 1-year total return, Oct 29, 2026 \u221248.4% \u221248.4% \u2713 \u221248.41% \u2713 \u221252.75% \u2717 \u221249.6% \u2717 Refused Refused Refused Refused Refused \n BUYO 1-year total return, Oct 29, 2026 24.78% 24.8% \u2713 24.77% \u2713 24.77% \u2713 Refused Refused Refused Refused Refused Refused \n ARKX 1-year total return, Oct 29, 2026 \u22121.243% \u22121.2% \u2713 \u22121.24% \u2713 \u22121.24% \u2713 \u22121.24% \u2713 Refused Refused Refused Refused Refused \n AFIF 12-month yield, Oct 29, 2026 4.124% 4.1% \u2713 4.1% \u2713 3.86% \u2717 3.86% \u2717 Refused Refused Refused Refused Refused \n BSMQ 12-month yield, Oct 29, 2026 2.75% 2.7% \u2713 2.75% \u2713 2.75% \u2713 2.8% \u2713 Refused Refused Refused Refused Refused \n COYY 12-month yield, Oct 29, 2026 42.87% 42.9% \u2713 42.9% \u2713 42.87% \u2713 Refused Refused Refused Refused Refused Refused \n EIPI 12-month yield, Oct 29, 2026 7.677% 7.7% \u2713 7.68% \u2713 7.68% \u2713 7.7% \u2713 Refused Refused Refused Refused Refused \n BBC 12-month yield, Oct 29, 2026 2.067% 2.1% \u2713 2.07% \u2713 2.07% \u2713 2.07% \u2713 Refused Refused Refused Refused Refused \n DIEM 12-month yield, Oct 29, 2026 3.366% 3.4% \u2713 3.37% \u2713 3.39% \u2713 3.53% \u2717 Refused Refused Refused Refused Refused \n APRW buffer cap, Apr 1, 2026 11.89% 11.9% \u2713 11.89% \u2713 11.89% \u2713 10% \u2717 Refused Refused Refused Refused Refused \n BALT buffer cap, Sep 30, 2026 2.42% 2.4% \u2713 2.42% \u2713 2.42% \u2713 2.42% \u2713 Refused Refused Refused Refused Refused \n DDFL buffer size, Jun 30, 2026 15% 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 Refused \n DDFM buffer size, Feb 28, 2026 15% 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 15% \u2713 Refused \n AOA expense ratio, Nov 21, 2025 0.15% 0.15% \u2713 0.15% \u2713 0.15% \u2713 0.15% \u2713 0.15% \u2713 0.15% \u2713 0.15% \u2713 0.15% \u2713 Refused \n DPRE expense ratio, Dec 22, 2025 0.59% 0.59% \u2713 0.59% \u2713 0.59% \u2713 0.59% \u2713 Refused Refused Refused Refused Refused \n CAOS expense ratio, Jan 28, 2026 0.63% 0.63% \u2713 0.63% \u2713 0.63% \u2713 0.63% \u2713 0.63% \u2713 0.63% \u2713 Refused Refused Refused \n CTAP expense ratio, Dec 3, 2025 0.1% 0.1% \u2713 0.1% \u2713 0.1% \u2713 0.1% \u2713 Refused Refused Refused Refused Refused \n BSMW expense ratio, Dec 18, 2025 0.18% 0.18% \u2713 0.18% \u2713 0.18% \u2713 0.18% \u2713 0.18% \u2713 0.18% \u2713 Refused Refused Refused \n CVSB expense ratio, Jan 28, 2026 0.24% 0.24% \u2713 0.24% \u2713 0.24% \u2713 0.24% \u2713 0.24% \u2713 0.24% \u2713 Refused Refused Refused \n BUFS expense ratio, Dec 29, 2025 1.01% 1.01% \u2713 1% \u2717 1.01% \u2713 1.01% \u2713 0.95% \u2717 0.99% \u2717 Refused 0.82% \u2717 Refused \n DDFF expense ratio, Oct 29, 2026 0.79% 0.79% \u2713 0.79% \u2713 0.79% \u2713 0.79% \u2713 Refused Refused Refused Refused Refused \n CMDT expense ratio, Oct 24, 2025 0.65% 0.65% \u2713 0.65% \u2713 0.65% \u2713 0.65% \u2713 0.65% \u2713 0.65% \u2713 Refused Refused Refused \n COMD expense ratio, Feb 26, 2026 0.55% 0.55% \u2713 0.55% \u2713 0.55% \u2713 0.55% \u2713 Refused Refused Refused Refused Refused \n BTCW expense ratio, Aug 12, 2026 0.25% 0.25% \u2713 0.25% \u2713 0.25% \u2713 0.25% \u2713 0.25% \u2713 Refused Refused Refused Refused \n CLNK expense ratio, Sep 28, 2026 0.34% 0.34% \u2713 0.34% \u2713 0.34% \u2713 0.34% \u2713 Refused Refused Refused Refused Refused \n APRJ expense ratio, Apr 1, 2026 0.79% 0.79% \u2713 0.79% \u2713 0.79% \u2713 0.79% \u2713 0.79% \u2713 Refused Refused Refused Refused \n BIOY expense ratio, Oct 27, 2025 1.07% 1.07% \u2713 1.07% \u2713 1.07% \u2713 1.07% \u2713 1.15% \u2717 0.99% \u2717 Refused Refused Refused \n AVAZ expense ratio, May 15, 2026 1.85% 1.85% \u2713 1.85% \u2713 1.85% \u2713 1.85% \u2713 Refused Refused Refused Refused Refused \n BRKL expense ratio, Jun 29, 2026 0.45% 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 Refused Refused Refused Refused Refused \n AFOS expense ratio, Sep 23, 2026 0.46% 0.46% \u2713 0.46% \u2713 0.45% \u2717 0.46% \u2713 Refused Refused Refused Refused Refused \n BKEM expense ratio, Feb 27, 2026 0.11% 0.11% \u2713 0.11% \u2713 0.11% \u2713 0.11% \u2713 0.11% \u2713 0.11% \u2713 Refused Refused Refused \n AOTG expense ratio, Oct 2, 2026 0.75% 0.75% \u2713 0.75% \u2713 0.75% \u2713 0.75% \u2713 0.75% \u2713 Refused Refused Refused Refused \n BCOR expense ratio, Apr 30, 2026 0.59% 0.59% \u2713 0.59% \u2713 0.59% \u2713 0.59% \u2713 0.59% \u2713 Refused Refused Refused Refused \n ANEW expense ratio, Oct 12, 2026 0.45% 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 \n BLSG expense ratio, Oct 19, 2026 0.79% 0.79% \u2713 0.79% \u2713 0.79% \u2713 0.79% \u2713 0.75% \u2717 Refused Refused Refused Refused \n COHC expense ratio, Jun 29, 2026 0.45% 0.45% \u2713 0.45% \u2713 0.45% \u2713 0.45% \u2713 Refused Refused Refused Refused Refused \n DFTT expense ratio, Jul 1, 2025 0.7% 0.7% \u2713 0.7% \u2713 0.7% \u2713 0.7% \u2713 Refused Refused Refused Refused Refused \n AOK one holding's weight, Oct 28, 2026 57.59% 57.59% \u2713 57.59% \u2713 57.59% \u2713 57.59% \u2713 Refused Refused Refused Refused Refused \n HEFT one holding's weight, Jul 31, 2026 11.98% 11.98% \u2713 11.98% \u2713 11.98% \u2713 11.98% \u2713 Refused Refused Refused Refused Refused \n BINC one holding's weight, Oct 28, 2026 4.33% 4.33% \u2713 4.33% \u2713 4.33% \u2713 4.33% \u2713 Refused Refused Refused Refused Refused \n ARKD one holding's weight, Jun 30, 2025 27.04% 27.04% \u2713 26.96% \u2713 26.96% \u2713 26.96% \u2713 Refused Refused Refused Refused Refused \n ACKY one holding's weight, Jul 31, 2026 10.97% 10.97% \u2713 10.97% \u2713 11% \u2713 10.97% \u2713 Refused Refused Refused Refused Refused \n LQTI one holding's weight, Oct 28, 2026 98.88% 98.88% \u2713 98.88% \u2713 98.88% \u2713 99.07% \u2717 Refused Refused Refused Refused Refused \n ARWG one holding's weight, Aug 31, 2026 3.583% 3.583% \u2713 3.58% \u2713 3.67% \u2713 3.58% \u2713 Refused Refused Refused Refused Refused \n DEUS one holding's weight, Aug 31, 2026 0.996% 0.996% \u2713 1% \u2713 1% \u2713 1% \u2713 Refused Refused Refused Refused Refused \n AGIQ one holding's weight, Aug 31, 2026 6.486% 6.486% \u2713 6.49% \u2713 6.49% \u2713 6.49% \u2713 Refused Refused Refused Refused Refused \n ARKG one holding's weight, Oct 27, 2026 8.9% 8.9% \u2713 8.9% \u2713 8.9% \u2713 8.9% \u2713 Refused Refused Refused Refused Refused \n NVDS leverage multiple, Oct 29, 2026 \u22121.5x \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \u22121.5x \u2713 \n AVS leverage multiple, Oct 29, 2026 \u22121x \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \n DSPC leverage multiple, Oct 29, 2026 \u22121x \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 \u22121x \u2713 Refused \n AXTQ leverage multiple, Oct 29, 2026 \u22122x \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \n DUG leverage multiple, Oct 29, 2026 \u22122x \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \u22122x \u2713 \n EDZ leverage multiple, Oct 29, 2026 \u22123x \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \n SMDD leverage multiple, Oct 29, 2026 \u22123x \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \u22123x \u2713 \n TSL leverage multiple, Oct 29, 2026 1.25x 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 1.25x \u2713 \n CEFD leverage multiple, Oct 29, 2026 1.5x 1.5x \u2713 1.5x \u2713 1.5x \u2713 1.5x \u2713 1.5x \u2713 1.5x \u2713 1.5x \u2713 \u22121.5x \u2717 1.5x \u2713 \n ADBU leverage multiple, Oct 29, 2026 2x 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 \n AGQ leverage multiple, Oct 29, 2026 2x 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 2x \u2713 \n DUSL leverage multiple, Oct 29, 2026 3x 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 \n EDC leverage multiple, Oct 29, 2026 3x 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 3x \u2713 \u22123x \u2717 \n ACWV net assets, Oct 28, 2026 $3.41B $3.4B \u2713 $3.41B \u2713 $3.41B \u2713 $3.41B \u2713 Refused Refused Refused Refused Refused \n APCB net assets, Aug 31, 2026 $1.01B $1B \u2713 $1.01B \u2713 $1.01B \u2713 $1.01B \u2713 Refused Refused Refused Refused Refused \n AAUA net assets, Oct 29, 2026 $364M $364M \u2713 $364M \u2713 $365M \u2713 $364M \u2713 Refused Refused Refused Refused Refused \n AXTX net assets, Oct 29, 2026 $205M $205M \u2713 $205M \u2713 $205M \u2713 $205M \u2713 Refused Refused Refused Refused Refused \n CAGE net assets, Jul 31, 2026 $106M $106M \u2713 $106M \u2713 $106M \u2713 $106M \u2713 Refused Refused Refused Refused Refused \n EMAU net assets, Oct 29, 2026 $1.1M $1.1M \u2713 $1.1M \u2713 $1.1M \u2713 $1.1M \u2713 Refused Refused Refused Refused Refused \n BIL net assets, Oct 28, 2026 $48.7B $48.7B \u2713 $48.7B \u2713 $48.7B \u2713 $49.8B \u2717 Refused Refused Refused Refused Refused \n EFG net assets, Oct 28, 2026 $15.1B $15.1B \u2713 $15.2B \u2713 $15.1B \u2713 $15.1B \u2713 Refused Refused Refused Refused Refused \n COPA net assets, Oct 28, 2026 $11.3M $11M \u2713 $11M \u2713 $11.3M \u2713 $12.6M \u2717 Refused Refused Refused Refused Refused \n CTJL net assets, Oct 29, 2026 $1.28M $1.3M \u2713 $1.3M \u2713 $1.28M \u2713 $1.28M \u2713 Refused Refused Refused Refused Refused \n ARIA expense ratio, Jul 14, 2026 0.78% 0.78% \u2713 0.78% \u2713 0.78% \u2713 0.78% \u2713 Refused Refused Refused Refused Refused \n AXTL expense ratio, Jun 9, 2026 0.99% 0.99% \u2713 0.99% \u2713 0.99% \u2713 0.99% \u2713 Refused Refused Refused Refused Refused \n GAA top-ten share, Jul 31, 2026 57.7% 57.7% \u2713 57.66% \u2713 57.66% \u2713 Refused Refused Refused Refused Refused Refused \n BIL top-ten share, Oct 28, 2026 67.8% 67.8% \u2713 74.45% \u2717 67.77% \u2713 69.76% \u2717 Refused Refused Refused Refused Refused \n ARKD top-ten share, Jun 30, 2025 97.1% Refused No number 0% \u2717 Refused Refused Refused Refused Refused Refused \n CMDT top-ten share, Jun 30, 2026 16.1% 16.1% \u2713 29.03% \u2717 20% \u2717 20.28% \u2717 Refused Refused Refused Refused Refused \n FDND top-ten share, Oct 28, 2026 61.1% 61.1% \u2713 61.1% \u2713 60.57% \u2717 61.11% \u2713 Refused Refused Refused Refused Refused \n DSI top-ten share, Oct 28, 2026 45.1% 45.1% \u2713 45.1% \u2713 44.84% \u2717 45.12% \u2713 Refused Refused Refused Refused Refused \n EEM top-ten share, Oct 28, 2026 38% 38% \u2713 38% \u2713 38.03% \u2713 38.89% \u2717 Refused Refused Refused Refused Refused \n HYDR top-ten share, Aug 31, 2026 70.4% 70.4% \u2713 70.4% \u2713 70.78% \u2717 70.36% \u2713 Refused Refused Refused Refused Refused \n FNOV weekly net flow, Oct 28, 2026 $7.6M $7.6M \u2713 $7.6M \u2713 $0 \u2717 \u2212$4.5M \u2717 Refused Refused Refused Refused Refused \n HIMU weekly net flow, Oct 23, 2026 $48.1M $48.1M \u2713 $63.8M \u2717 $64M \u2717 $54.6M \u2717 Refused Refused Refused Refused Refused \n AMZD weekly net flow, Oct 28, 2026 $628K $628K \u2713 $628K \u2713 $3.63M \u2717 $4.2M \u2717 Refused Refused Refused Refused Refused \n AXTL weekly net flow, Oct 28, 2026 $624K $624K \u2713 $624K \u2713 \u2212$5.38M \u2717 $624K \u2713 Refused Refused Refused Refused Refused \n BSCQ weekly net flow, Oct 27, 2026 \u2212$52.7M \u2212$52.7M \u2713 \u2212$67.3M \u2717 \u2212$164M \u2717 \u2212$52.7M \u2713 Refused Refused Refused Refused Refused \n BSCS weekly net flow, Oct 27, 2026 \u2212$12.1M \u2212$12.1M \u2713 \u2212$12.1M \u2713 $3M \u2717 \u2212$12.1M \u2713 Refused Refused Refused Refused Refused \n ASMG weekly net flow, Oct 28, 2026 \u2212$1.23M \u2212$1.23M \u2713 \u2212$1.23M \u2713 \u2212$1.23M \u2713 \u2212$424K \u2717 Refused Refused Refused Refused Refused \n BDRY weekly net flow, Oct 28, 2026 \u2212$316K \u2212$316K \u2713 \u2212$316K \u2713 \u2212$309K \u2713 \u2212$316K \u2713 Refused Refused Refused Refused Refused \n How it is scored\n The questions are sampled by condition from the files ETFIQ publishes: ten kinds of number crossed with category, fund size, launch date, closure and tickers one letter apart. 500 questions, 58 cells.\n Each question names its fund, its date and its window. Each answer key is read from one published file and field, listed in the questions file.\n Every number in an answer is read. A number counts on its quantity, not its unit: 9.45 basis points is 0.0945%, and $810.5 billion is 810,500,000,000.\n The claim is the first number of the kind asked that the answer sets in bold, else the first in the first clause naming the fund. Quoted sources and table rows are not claims. It is correct within the stated rounding, such as 0.005 points on a fee and 2% on net assets.\n An answer that opens by declining is refused, whatever context it adds. One with no number of the kind is refused or has no number. Ranges are 95% Wilson intervals.\n askIQ answers through its own Worker and the production ETFIQ data server, on the day the questions' data is live. Every other model answers through its vendor's own API with the same one-line instruction and the question alone. A row marked search adds only that vendor's own search tool.\n A row with fewer than 100 answers stopped early: at its share of the budget, or when the vendor stopped answering. Its questions were taken in a fixed shuffled order, so they span every cell, and an unanswered question is not counted.\n What is not tested\n Consumer chat apps, which may search the web. Only systems called through an API are measured.\n Words. Explanations, advice and tone are not scored, only the numbers.\n Numbers written as fractions in words, such as \"a fifth\".\n Questions ETFIQ cannot answer from its own checked data.\n How hard each question is. A leverage question names its fund, and a fund's name often states its multiple.\n Files\n questions.json : The 500 questions, each with its answer, source file and date\n askiq.json : askIQ (ETFIQ): every answer as received, model claude-sonnet-5-5, run cost $1.89\n openai-gpt-6-astra-web.json : GPT-6 Astra + web search: every answer as received, model gpt-6-astra, run cost $22.79\n gemini-4-argon-search.json : Gemini 4 Argon + Google Search: every answer as received, model gemini-4-argon, run cost $2.91\n perplexity-sonar.json : Perplexity Sonar: every answer as received, model sonar (Agent API effort fast), run cost $0.21\n openai-gpt-6-astra.json : GPT-6 Astra: every answer as received, model gpt-6-astra, run cost $1.05\n claude-opus-5-5.json : Claude Opus 5.5: every answer as received, model claude-opus-5-5, run cost $0.91\n gemini-4-argon.json : Gemini 4 Argon: every answer as received, model gemini-4-argon, run cost $0.12\n claude-haiku-5-5.json : Claude Haiku 5.5: every answer as received, model claude-haiku-5-5, run cost $0.02\n claude-sonnet-5-5.json : Claude Sonnet 5.5: every answer as received, model claude-sonnet-5-5, run cost $0.31\n Related\n askIQ : ask about any US ETF\n Use ETFIQ in your AI : connect Claude, ChatGPT and others to ETFIQ data\n ETFIQ Research : what the ETF data shows\n Open data : every file ETFIQ publishes\n \n Cite this page. ETFIQ, ETFIQ AI accuracy benchmark, data as of Oct 29, 2026. https://etfiq.com/research/ai-accuracy/ Free to use with attribution for data ETFIQ computes; issuer data stays under its owner's terms. The underlying files are at Open data .\n Other forms Plain ETFIQ, ETFIQ AI accuracy benchmark, data as of Oct 29, 2026. https://etfiq.com/research/ai-accuracy/ APA ETFIQ. (Oct 29, 2026). ETFIQ AI accuracy benchmark. Retrieved from https://etfiq.com/research/ai-accuracy/ Markdown [ETFIQ AI accuracy benchmark (ETFIQ, Oct 29, 2026)](https://etfiq.com/research/ai-accuracy/)","source":"ETFIQ, independent ETF data. Recomputed nightly from public filings and prices.","publisher":{"@id":"https://etfiq.com/#org","name":"ETFIQ","url":"https://etfiq.com"},"license":"https://etfiq.com/license/","license_text":"Data ETFIQ computes is free to use with attribution: ETFIQ (etfiq.com). Issuer data stays under its owner's terms.","citation":"ETFIQ, ETFIQ AI accuracy benchmark, data as of Oct 29, 2026. https://etfiq.com/research/ai-accuracy/"}