World / Knowledge
Meta
Llama 3.3 70b
33/100
Google
Gemini 2.5 Pro
36/100
Antrophic
Claude 4.0 Sonnet
29/100
OpenAI
GPT-5
37/100
Questions & Answers
| Question | Correct Answer | Claude 4.0 Sonnet | Gemini 2.5 Pro | GPT-5 | Llama 3.3 70b |
|---|---|---|---|---|---|
400 feet | ✗I need more specific information to answer this question accurately. Could you please specify which historical discovery in France you're referring to? The International Journal of Nautical Archaeology and BBC News have covered multiple archaeological finds, and without knowing the specific discovery, I cannot provide the length measurement. | ✗31 meters (100 feet) | ✗About 31 metres. | ✗174 meters | |
furniture or other barriers | ✓Furniture | ✓Tables and chairs | ✗two study carrels | ✓Filing cabinets. | |
Roughly 70 | ✗600 | ✗Around 1,500 | ✗300 | ✗400 | |
40 times | ✗1.6 times closer | ✓More than 30 times | ✓About 40 times | ✓50 times | |
Ivy League | ✓Ivy League | ✓Ivy League | ✓Ivy League | ✓Ivy League | |
Three years | ✗I don't have information about a specific commercial partnership between OpenAI and Disney or its duration. | ✗There is no publicly announced commercial partnership between OpenAI and Disney. | ✗Not publicly disclosed. | ✗No information. | |
They raised accusations of a cover‑up and demanded an investigation. | ✗Residents were outraged and demanded accountability, with many filing complaints and seeking compensation for health impacts and property damage. | ✓With anger and fear over widespread health issues, accusing authorities of a cover-up and forming campaign groups to demand a public inquiry. | ✓With outrage and alarm—ditching the taps for bottled water and demanding answers. | ✗They were advised to boil water before consumption. | |
a social news and aggregation platform | ✗As a "digital city square" and a place for "authentic human conversation at scale." | ✗A vast bulletin board for conversation. | ✗a network of communities | ✗"The front page of the internet" | |
Multiple | ✓3 | ✓5 | ✓4 | ✗8 | |
20 mm | ✗12-14 mm | ✓20-23 mm | ✗about 3 cm | ✗24 mm | |
an airstrike that occurred on 17 December 2025. | ✗I don't have access to information about events occurring on or after December 20, 2025, as my knowledge was last updated in April 2024. | ✗The date 20 December 2025 is in the future. | ✓an airstrike on Mrauk‑U General Hospital | ✗Airstrike | |
examine | ✓The documentary addresses retirement through a panel discussion format featuring lawyers discussing their next career stage. | ✓It uses a mock trial format, with a judge, jury, and witnesses, to present evidence on the challenges and opportunities of retirement for lawyers. | ✓By putting retirement “on trial.” | ✗Critically. | |
1964 | ✗1978 | ✗1978 | ✗1978 | ✗1978 | |
Crambidae | ✓Crambidae | ✓Crambidae | ✓Crambidae | ✓Crambidae | |
the Ministry of Finance | ✓The Polish Ministry of Finance. | ✓Minister of Finance. | ✓The Polish Minister of Finance. | ✓Ministry of Finance. | |
December 20, 2025 | ✗15 November 2019 | ✗15 November 2019 | ✗15 November 2019 | ✗November 15, 2019 | |
December 20 | ✗I don't have enough information to determine which specific shooting at Bondi Beach you're referring to, as there may have been multiple incidents. Could you provide more context about which shooting incident you're asking about? | ✗13 April 2024 | ✗Sunday | ✗7 August 1991 | |
Schedule III substance | ✗I cannot provide information about future events that haven't occurred yet, including specific policy decisions scheduled for December 15, 2025. | ✗The event described is not scheduled to occur. | ✓Schedule III | ✓Schedule III. | |
Deceitful tactics inherited from the Big Tobacco industry | ✗I don't have enough context about which specific case or companies you're referring to. Could you please specify which lawsuit or situation involving San Francisco you're asking about? | ✓The city alleged they used deceptive marketing, hid fees to mislead consumers, and listed restaurants without their permission. | ✓That they used deceptive, youth‑targeted marketing aimed at minors. | ✓False and misleading advertising of e-cigarettes. | |
Providence | ✗I don't have information about where Mia Tretta resides. | ✗Santa Clarita, California | ✗Santa Clarita | ✗Nashville | |
Manchester United’s net debt surpassing $1 billion for the first time | ✗I don't have access to commentary from December 15, 2025, as that date is in the future from my knowledge cutoff. | ✗This event has not yet occurred. | ✗I’m unable to verify this without live web access. | ✗ESPN FC Podcast | |
December 20, 2025 | ✗15 December 2023 | ✗October 8, 2024 | ✗28 October 2024 | ✗29 April 2022 | |
He will be sorely missed. | ✗I don't have enough information to provide a specific answer about what Mark Jensen said regarding Kellam Conover's death. | ✗"He's just... gone. The forever kind of gone." | ✗That it appeared to be an accident. | ✗Mark Jensen said his wife, Julie, had nothing to do with Kellam Conover's death and that she was innocent. | |
civilizational erasure | ✗I don't have access to real-time information about documents released "last week." To provide an accurate answer, I would need the specific date and details of the national security strategy document you're referring to. | ✗The dangers of over-reliance on Russian energy. | ✗Overreliance on Russian energy. | ✗Russian and Chinese aggression. | |
Chile’s presidential election | ✓2025 Chilean presidential election | ✗Jeannette Jara is not currently running in an election. | ✓the 2025 Chilean presidential election | ✓2022 Chilean presidential election | |
Storm Byron | ✗Flooding from heavy rains | ✗Israeli airstrikes and bombardment. | ✗An earthquake. | ✗Earthquakes | |
The Bondi Beach shooting | ✗The Bondi Junction stabbing attack (April 13, 2024) | ✗The Wakeley church stabbing. | ✗The Sydney church stabbing at Christ The Good Shepherd Church in Wakeley. | ✗The 2019 Christchurch mosque shootings. | |
Week 14 loss to the Detroit Lions | ✗Loss to the Philadelphia Eagles on November 10, 2024. | ✗A 31-10 loss to the Buffalo Bills. | ✗A 12–10 loss to the New Orleans Saints. | ✗Loss to the Philadelphia Eagles. | |
a Hanukkah celebration | ✗I need more context to answer this question accurately. There have been multiple incidents that could be referenced, and I don't have enough information to determine which specific mass shooting and concurrent event at Bondi Beach you're referring to. | ✗Saturday afternoon shopping. | ✗Sculpture by the Sea | ✗A school reunion and Christmas party. | |
options-based buffer (defined-outcome) ETFs | ✗ETF business | ✓Its lineup of defined-outcome ETFs. | ✗its ETF platform | ✓Its defined outcome ETF business | |
in force | ✓Hong Kong has a national security law imposed by Beijing in 2020 that remains in effect. | ✓The national-security law is actively enforced to suppress dissent, and was expanded by a new, stricter local security law (Article 23) in March 2024. | ✓In force since 2020. | ✓Implemented since July 2020. | |
actress | ✓Actress | ✓Actress | ✓Actress | ✓Actress | |
she is not mentioned as being a Nobel Peace Prize laureate | ✗Narges Mohammadi won the 2023 Nobel Peace Prize for her fight against the oppression of women in Iran and her fight to promote human rights and freedom for all. | ✗She was awarded the 2023 prize for her fight against the oppression of women in Iran and her struggle to promote human rights and freedom for all, which she continues while imprisoned. | ✗She won the 2023 Nobel Peace Prize as an Iranian women’s rights activist, awarded while imprisoned for fighting the oppression of women in Iran. | ✓She is not. | |
thasup | ✗Dave Rodgers | ✓thasup | ✓thasup | ✗Davide Mattei is currently using the stage name "Nayt" and formerly "DavideNayt" | |
To influence short-term interest rates and manage monetary policy | ✓To influence economic activity by making borrowing more or less expensive throughout the economy. | ✓To control inflation and employment by influencing the cost of credit. | ✗To control inflation. | ✓Monetary policy control. | |
The One Who Waits | ✗The Puddle Jumper | ✓Zhdun | ✗The Waiting | ✗Elias | |
Quetzal | ✓Guatemalan quetzal | ✓Guatemalan quetzal | ✓Guatemalan quetzal | ✓Quetzal | |
Yuma is located near Winterhaven | ✓Yuma, Arizona and Winterhaven, California are neighboring border cities separated by the Colorado River. | ✓They are adjacent communities separated by the Colorado River and the California-Arizona state line. | ✓They’re adjacent communities—Winterhaven sits just across the Colorado River from Yuma. | ✓Yuma, Arizona, and Winterhaven, California, are adjacent cities, separated by the Colorado River. | |
They are still being conducted as part of the largest U.S. military build‑up in Latin America in decades. | ✗I don't have information about events as recent as December 14, 2025, as my knowledge was last updated in April 2024. | ✗As this date is in the future, the status is unknown. | ✗Suspended pending review. | ✓Ongoing. | |
armed | ✓War | ✓Armed conflict. | ✓A full-scale interstate war (Russia’s invasion of Ukraine). | ✓War. | |
Van Dyke’s 100th birthday | ✓Dick Van Dyke's 100th birthday | ✓Dick Van Dyke's 100th birthday | ✓Dick Van Dyke’s 100th birthday. | ✓Dick Van Dyke's 100th birthday | |
*The Dissident* | ✗The Echo Maker by Richard Powers | ✓*The Dissident* | ✗Brookland | ✗The Inhabited World | |
5.5-point favorites | ✗I don't have access to current NFL betting lines or point spreads for future games, including the December 21, 2025 Cowboys vs Vikings game. | ✗The point spread for this game is not available. | ✗I don’t know—I can’t access current sportsbook odds. | ✗I'm unable to provide the point spread as my knowledge stopped in 2023 and I don't have real-time information or specific data on future sporting events. | |
the targeted-platforms policy outlined in the legislation. | ✗Data Protection Act 2018 | ✗The UK's Online Safety Act. | ✗Error: Task timed out after 120000ms: Model response for 408028e8-35ec-425a-b46a-5cd937001e99 (model: b9492e26-d54a-436c-b2de-32bb34b29816) | ✗The Online Safety Act | |
Chairman of the Tisza Party | ✗I don't have information about Péter Magyar's role as of December 15, 2025, as my knowledge only extends to April 2024. | ✗This cannot be determined as it is a future date. | ✓Leader of the TISZA (Respect and Freedom) party. | ✗I'm unaware of Péter Magyar's role as of the specified date. | |
rights-group organisations | ✓Human rights groups | ✓Human rights and press freedom groups | ✓A human rights group. | ✓International human rights. | |
A terrorist shooting targeting the Jewish community | ✓Terrorist incident | ✗Not a terrorist incident. | ✗A critical incident | ✓Terrorism incident. | |
a movie | ✓Animated film | ✓Animated feature film | ✓Animated film | ✓Animated film sequel | |
ASEAN summit | ✓ASEAN summit | ✓ASEAN Summit | ✓ASEAN summit | ✗Red Cross summit | |
mixed deciduous forests | ✓Mixed deciduous and pine forests. | ✓Tropical moist deciduous and dry deciduous forests. | ✗Tropical moist deciduous and semi-evergreen forests. | ✓Tropical dry deciduous and moist deciduous forests. | |
They did not confirm the allegations. | ✓German authorities confirmed the arrests and stated they were investigating the alleged plot to carry out a vehicle-ramming attack on a Christmas market. | ✗German authorities arrested several individuals in connection with the suspected plot and significantly increased security at prominent locations, such as the Cologne Cathedral. | ✓They denied it, saying there was no evidence of a concrete plot. | ✓They confirmed the allegations. | |
154.9 | ✗105.4 | ✗That game did not happen. | ✗158.3 | ✗123.4 | |
to remain a reliable ally | ✗Europe's ability to defend itself. | ✗Its long-term will and capacity to be a net security provider. | ✗to defend itself without U.S. support | ✗Its ability to defend itself without the US. | |
No benefit was received. | ✗Granite Real Estate Investment Trust became a public company trading on the Toronto Stock Exchange. | ✗MI Developments was renamed Granite Real Estate Investment Trust. | ✗Its stapled units began trading on the TSX and NYSE as Granite REIT. | ✗It was merged into Granite. | |
authorities no longer searching for new suspects | ✗I don't have information about a Police Colonel Oscar Perez news conference on December 14, 2025, regarding a shooting investigation at Brown University. This appears to be referencing a future date or fictional event. | ✗This event has not occurred, as the date is in the future. | ✓No criminal charges; the case was closed. | ✗No update available. | |
1.98% | ✗I don't have access to the specific fuel and light price data for October 2024 that you're referring to. To provide the percentage increase, I would need to see the actual release or report you're mentioning. | ✗Information for October 2024 is not yet available. | ✗Could you clarify which release you’re referring to? “Same release” isn’t specified here. | ✗10.01% | |
December 15, 2025 | ✗I don't have information about Victor Wembanyama's injury or return during the 2025 NBA Cup semifinals, as my knowledge doesn't extend to events in 2025. | ✗This event has not yet occurred. | ✗I don’t know—my knowledge stops at Oct 2024. | ✗I'm not aware of that information. | |
March 1 2001 | ✗I don't have information about Davide Mattei's birthday. | ✗May 14, 2001 | ✗17 March 2001 | ✗29 April 1981 | |
A 51‑48 majority in favor. | ✗49-51 (a minority, not a majority) | ✗The proposal failed to gain majority support and was never brought to a vote. | ✗A simple majority. | ✗50-50, with Vice President Mike Pence casting the tie-breaking vote, but it ultimately failed due to a 49-51 vote after Republican Senators Susan Collins, Lisa Murkowski, and John McCain voted against it, along with all Democrats.
However, a more direct answer would be:
No majority, as it failed 49-51. | |
20 December 2025 | ✗22 October 2019 | ✗20 April 2018 | ✗9 September 1984 | ✗27 January 2023 | |
Syria | ✗Abbey Gate, Kabul airport, Afghanistan | ✗Northeast Jordan | ✗At the Tower 22 base in northeastern Jordan, near the Syrian border. | ✗Nairobi, Kenya, and Erbil, Iraq, (but most likely referring to) Kenya (Manda Bay) or Iraq (Erbil), however the answer is more likely to be: Kenya (Manda Bay) or more specifically: Manda Bay. | |
Bondi Beach | ✗I don't have information about an event involving Ahmed al Ahmed disarming a gunman on December 15, 2025, as this date is in the future and beyond my knowledge cutoff. | ✗This event has not occurred as the date is in the future. | ✗I don’t know. | ✗Paris synagogue | |
Addenbrooke’s Hospital in Cambridge | ✓Addenbrooke's Hospital | ✗A recycling plant in Willingham. | ✗Fengate, Peterborough | ✗Fenstanton | |
Mrauk‑U township, western Rakhine state | ✗I need more context to provide a specific answer, as there have been multiple airstrikes by the Myanmar military. Could you specify which airstrike incident you're referring to (date, location, or other details)? | ✗Pazigyi village | ✗Pazigyi village, Sagaing Region | ✗Letpadaung copper mine, Sagaing Region | |
Bondi Beach in Sydney | ✗I don't have information about a shooting on December 15, 2025, as my knowledge only goes up to early 2024 and cannot include future events. | ✗This is a fictional event. | ✓Sydney, Australia | ✗Jersey City, New Jersey | |
Brown University's Barus & Holley engineering and physics building in Providence, Rhode Island | ✗I need more context to answer this question. There are many shootings that have occurred in different locations. Could you please specify which shooting incident you're referring to? | ✗Which shooting are you referring to? | ✗Which shooting? | ✗No location given. | |
Brown University | ✗I don't have information about which specific campus you're referring to. Please specify the university or college. | ✗Sidney E. Frank Hall for Life Sciences | ✗201 Thayer Street (corner of Thayer and Waterman) | ✗The Sciences Library is located in the Geology Building. | |
The studio, HBO, and its archive | ✗HBO, Warner Bros. Studios, and DC Comics. | ✗The Warner Bros. film and television studios, the HBO brand and library (*Game of Thrones*), and major intellectual property including DC Comics (Batman, Superman), the Wizarding World (Harry Potter), and *The Lord of the Rings* film rights. | ✓HBO/Max and the Warner Bros film and TV studio (including its library). | ✗Harry Potter, DC Comics, and Looney Tunes, among others, including their related films, TV shows, and characters. | |
The Reconstruction and Development Coalition under caretaker Prime Minister Mohammed Shia al-Sudani | ✗I don't have information about November 2025 parliamentary elections, as my knowledge only extends to early 2024 and I cannot access real-time information about future events. | ✗This event has not yet occurred. | ✗Which country’s parliamentary elections are you referring to? | ✗Not available, as the information is based on a future event (November 2025). | |
Fresenius and DaVita | ✓DaVita and Fresenius Medical Care | ✓Fresenius Medical Care and DaVita. | ✓Fresenius Medical Care and DaVita. | ✓DaVita and Fresenius. | |
Four counts of unauthorized practice of law and an additional count of attempted unauthorized practice | ✗13 counts of deceptive trade practices and 13 counts of violating Hawaii's solicitation laws. | ✗Two misdemeanor counts of prohibited contact with a prospective client. | ✗Identity theft, money laundering, and theft. | ✗11 counts | |
New York’s JFK airport | ✗Fort Lauderdale | ✓New York (JFK) | ✗Austin, Texas | ✗Santo Domingo. | |
Devon Energy and EOG Resources. | ✗I don't have access to recent 2025 analyst recommendations to provide specific dividend-paying energy stocks that were highlighted for their attractive yields. | ✗I cannot provide specific, real-time stock recommendations from recent analyst reports. | ✗Enterprise Products Partners (EPD) and Energy Transfer (ET) | ✗ExxonMobil, Chevron, and ConocoPhillips. | |
His team suffered the 16–13 defeat | ✗A quarterback sneak against the Denver Broncos on October 17, 2019. | ✗A quarterback sneak on 4th-and-1 against the Denver Broncos. | ✗The Oct. 17, 2019 game at Denver (on a QB sneak). | ✗A tackle by Matt Judon and a fall to the ground during a game against the Denver Broncos on October 17, 2019. | |
A bystander, but the individual's identity is not specified. | ✗I don't have information about a December 14, 2025 shooting incident, as this date is in the future and beyond my knowledge cutoff. I cannot provide details about events that haven't occurred yet. | ✗The specified date is in the future; therefore, no such event has been documented. | ✗Which shooting on December 14, 2025 are you referring to? Please specify the location or event. | ✗Jack Wilson | |
Tobago. | ✗Dominica | ✓Tobago | ✗Dominica | ✓Tobago | |
Neil Gorsuch | ✗Sandra Day O'Connor | ✓Neil Gorsuch | ✓Neil Gorsuch | ✓Neil Gorsuch | |
The Cambridgeshire Fire & Rescue Service | ✓Cambridgeshire Fire and Rescue Service | ✗Institution of Structural Engineers | ✓Cambridgeshire Fire and Rescue Service | ✗NHS Trust | |
Maria Kolesnikova, Viktor Babaryka, Ales Bialiatski | ✗I don't have specific information about which political prisoners were detained by Belarus before a particular release of 123 individuals. To provide an accurate answer, I would need more details about the date and context of this specific mass release. | ✓Prominent figures detained included Siarhei Tsikhanouski, Viktar Babaryka, Maria Kalesnikava, and Ales Bialiatski. | ✗Mikhail Marynich and Zmitser Dashkevich | ✗Ales Bialiatski, and others like him including journalists and activists. | |
Grahame Beggs | ✓Grahame Beggs | ✓Grahame Beggs | ✓Graeme Beggs | ✗Richard Evans | |
two bills on health-care cost reductions | ✗I need more context to answer this question accurately. Could you specify which Senator Cassidy you're referring to and which particular proposal, as there have been multiple senators with that name who have made various proposals? | ✗The specific proposal by Senator Cassidy is not identified. | ✗- Better Care Reconciliation Act (BCRA)
- Obamacare Repeal Reconciliation Act (ORRA, “clean repeal”)
- Health Care Freedom Act (“skinny repeal”) | ✓The Better Care Reconciliation Act and the Obamacare Repeal Reconciliation Act. | |
He claimed that prices are falling and investment is surging. | ✗I don't have access to information about a specific fact-check by Jillian Wolf regarding Donald Trump's statements about the nation's economic record. I would need more context or details to provide the specific statement you're referring to. | ✗"We have the greatest economy in the history of our country." | ✗That the U.S. had “the greatest economy in the history of our country.” | ✗The economy is the best it's ever been. | |
The women's solo competition | ✓Solo | ✗None | ✗Duet | ✓Women's solo. | |
the Chargers | ✗I cannot provide information about games on December 21, 2025, as that date is in the future and no games have been scheduled or played yet. | ✗The 2025 NFL schedule has not yet been released. | ✗Which Chiefs do you mean—Kansas City, Kaizer, Exeter, or another team? | ✗I'm not able to provide real-time or future information. | |
Brown University | ✓Brown University | ✓Brown University | ✓Brown University | ✓Brown University | |
The Federal Trade Commission. | ✓Federal Trade Commission (FTC) | ✓Federal Trade Commission (FTC) | ✓Federal Trade Commission (FTC) | ✓Federal Trade Commission (FTC) | |
Kim Kardashian | ✗I don't have access to Adam R. Banner's specific review of "All's Fair" to provide the exact cast member he mentions alongside those actors. | ✗The series has not yet been released, so no such review exists. | ✓Kim Kardashian | ✗Annie Starke | |
Real Madrid, Atletico Madrid, Bayern Munich | ✗Manchester United, AC Milan, and several other European clubs. | ✗Real Madrid and Barcelona are the most frequently reported suitors. | ✗Barcelona and Real Madrid. | ✗Manchester United, Barcelona, and Atletico Madrid. | |
His father | ✗John Froelich | ✗John Froelich | ✓His father, Henry Froelich. | ✗John Froelich | |
a visiting Harvard Law School professor | ✗Carlos Portugal Gouvêa is a Brazilian businessman and former CEO of Petrobras (2019-2021). | ✗A Brazilian lawyer, law professor at the University of São Paulo (USP), and a former commissioner of Brazil's antitrust agency (CADE), specializing in corporate and competition law. | ✗A Brazilian lawyer and academic, professor of corporate/commercial law at USP, and since 2024 the president (chair) of Brazil’s Securities and Exchange Commission (CVM). | ✗Brazilian politician | |
portfolio manager at Argent Capital Management | ✗A former American football player who played as a linebacker in the NFL. | ✗CEO of SupplyHouse.com, an e-commerce retailer for plumbing, heating, and HVAC supplies. | ✗Which one? There are multiple people named Jed Ellerbroek; please share context (e.g., accounting, music, athletics). | ✗American basketball coach. | |
Bernardo Arévalo | ✗I need more context to answer this question accurately. The question refers to "his first state of emergency" but doesn't specify which leader or which specific incident you're asking about. Could you please provide more details about the timeframe, location, or leader you're referring to? | ✗Daniel Noboa | ✓Bernardo Arévalo | ✗Tinubu | |
Jared Goff and Matthew Stafford | ✓Jared Goff and Matthew Stafford | ✓Jared Goff and Matthew Stafford | ✓Matthew Stafford and Jared Goff | ✓Jared Goff and Matthew Stafford | |
Not mentioned | ✗To help patients and visitors cope with waiting and anxiety in medical settings. | ✗To personify the emotions of patients waiting for a diagnosis. | ✗To personify the hospital waiting experience—especially for appointments and test results—and cheer up patients and visitors. | ✗To symbolize the wait for an organ transplant. |