Just when you started coming to terms with ChatGPT's eerie capabilities,Watch I was dragged into prison by my ex OpenAI dropped a new version of its AI language model.
OpenAI says GPT-4 is much more advanced than GPT-3, which powers ChatGPT. And to prove it, they made GPT-4 sit down for a bunch of exams. OpenAI tested GPT-4 with a variety of standardized tests from high school to graduate to professional level and spanning across mathematics, science, coding, history, literature, and even the one you take to become a sommelier. The exams were comprised of multiple choice and free-response question and GPT-4 was scored using the standard methodology for each exam.
SEE ALSO: How to get access to GPT-4 right nowPut your pencil down, GPT-4, it's time to see check your scores.
GPT-4 didn't just get into law school, it passed the bar. The AI language model scored in the 88th percentile on the LSATs (Law School Admission Test) and did even better on the Bar (Uniform Bar Exam) by scoring in the 90th percentile. By comparison, GPT-3 was in the bottom 40 percent of the LSATs and 10 percent on the Bar.
GPT-4 took both the math and reading/writing sections of the SATs and all three sections of the GREs which are broken down into quantitative, verbal, and writing skills. It scored in the 80th or 90th percentile of all sections except for the writing section of the GREs... which it kind of bombed in the 54th percentile.
The quintessential overachiever, GPT-4 also took allthe AP (Advanced Placement) high school exams. It aced most of them, scoring between the 84th and 100th, except for a few outliers.
GPT-4 scored 44th in AP English Language and a measly 22nd in AP English Literature. So all you wordsmiths out there might have some more time before GPT-4 replaces you. GPT-4 didn't do so hot on AP Calculus BC scoring between 43rd and 59th, proving that even for a supercomputer, calculus is not easy. But that still earns GPT-4 a four, so it might still place out of college calculus.
GPT-4 still has some work to do with its coding skills, which is curious since one of its marketed uses is for helping developers. Its rating for Codeforces, which hosts competitive programming events, is 392, which puts it way down in the Newbie category of anything below 1199.
It did pretty well on the easy level of the Leetcode (31 out of 41 problems solved) but struggled when it came to medium or hard level of difficulty (21/80 and 3/45 respectively). As we saw in the developer demo livestream, GPT-4 is fully capable of writing Python, but required some manual tweaking to set the right parameters, which might explain some these test scores. Or maybe it didn't eat breakfast that morning.
GPT-4 passed the sommelier exams with flying colors. It placed lowest (77th percentile) in the most advanced sommelier exam. But for a non-human entity that's never tasted wine, we'll let that one slide.
OpenAI has released a full breakdown of how GPT-4 performed. GPT-4 might not write the next great American novel...yet, but GPT-4's future as a mathematically brilliant lawyer and wine connoisseur looks pretty bright.
Topics Artificial Intelligence ChatGPT
Previous：Mary Shows Up
A worthless juicer and a Gipper-branded server
Help! My Friend Is a Vaper: Advice from ‘The Paris Review’
Voyage in the Dark by Brian Cullman
Edward Albee Wanted His Unfinished Work to Be Destroyed
The 10 Most Anticipated PC Games of 2016
The Poetry of Icebergs
The Poetry of Icebergs
Daily Cartoon: 1439, Movable Type
Outdoor speaker deal: Save $20 on the Soundcore Boom 2
How Eleanor Perry Changed the Way We Saw Women in the Movies
Skype is finally shutting down
Blue Shores: On the Photography of Stephen Shore
Satellites Are Spinning: Notes on a Sun Ra Poem
Peter Matthiessen’s Notebook, Lost and Found
Best robot vacuum deal: Save $200 on Eufy X10 Pro Omni robot vacuum
Can AI Write Pop Songs? On Music and Machine Language
The Case of the Purloined Portrait
A New Museum Memorializes the Commercial World’s Biggest Failures
AMD Radeon RX 550 + Intel Pentium G4560
It’s Time to Get in Touch with Your Inner Grotesque
Ralph Ellison and Joseph Mitchell: A Friendship Hiding in the ArchivesMe for the Woods: Into the Wilderness for Thoreau’s BicentennialCharles and Ray Eames’ Films Shine a Light on Their Design PhilosophyShakespeare: Dead for 401 Years and Still Getting Hate MailThe Designs of the Jazz Age (It Wasn’t All Cocktail Shakers and Dresses)How John King’s String Quartet Fuses Western and Arabic MusicHumanities Majors: the Silicon Valley Cult Wants to Eat Your BrainDaily Cartoon: 1880, BrailleVoyage in the Dark by Brian CullmanHelp! My Friend Is a Vaper: Advice from ‘The Paris Review’Staff Picks: Paleoart, Mark Twain, Writers’ Workspaces, and MoreHumanities Majors: the Silicon Valley Cult Wants to Eat Your BrainThe Uncanny Double: An Interview with Megan McDowellStaff Picks: Alec Wilkinson, Ali Smith, Long Ling, and MorePour One Out for Branwell Brontë—the Guy Gets No RespectIn Memory of “In Memory of Leopardi”Staff Picks: David Grossman, Donald Barthelme, Derren Brown, and MoreDeborah Turbeville’s AntiPaleoart: Visions of a Prehistoric PastVoyage in the Dark by Brian Cullman The Being of the Sentence Reading the Police Blotter Emoji Poetry Contest Tuli Kupferberg’s Yeah!: The Tiny Magazine That Captured the 1960s by Alex Zafiris Revisited: Watership Down Dominique Nabokov Photographs Artists’ Living Rooms The Inventions of Witches This Girl Is on Fire: Germany’s Creepiest Children’s Poem Dear Lynda: Loveless Triangles and Hopeless Indecision by Lynda Barry An Interview with Kerri Pierce Book Ideas from the Bottom of the Barrel Death’s Footsteps How the Grinch Self Reading Between the Lines: “Gilded Age Drawings at the Met” What Is the Political Responsibility of the Artist? by Taylor Plimpton Painting the American Dream at Guantánamo by Paige Laino Playing for Ralph Ellison's Little Man at Chehaw Station The Tenuous Nonfiction of Clarice Lispector's Crônicas Degas’s Model Tells All The Dignified Bot
2.6062s , 10131.4765625 kb
Copyright © 2025 Powered by 【Watch I was dragged into prison by my ex】,Creation Information Network