인류의 마지막 시험 (Humanity's Last Exam): AI의 한계를 넘어서
본 기사는 최첨단 AI 모델의 능력을 평가하는 새로운 벤치마크인 '인류의 마지막 시험(HLE)'의 개발과 그 의미를 다룹니다. HLE는 기존 벤치마크의 한계를 극복하고 AI 연구 및 정책 수립에 기여할 것으로 예상됩니다.

인류의 마지막 시험: AI 시대의 새로운 척도
최근 급속도로 발전하는 대규모 언어 모델(LLM)의 능력을 평가하는 벤치마크의 중요성이 커지고 있습니다. 하지만 기존의 MMLU와 같은 벤치마크는 LLM이 이미 90% 이상의 정확도를 달성하여, 최첨단 기술의 실력을 제대로 측정하는 데 한계가 드러났습니다. 이러한 문제를 해결하고자, 전 세계의 다양한 분야 전문가들이 모여 새로운 벤치마크, **'인류의 마지막 시험(Humanity's Last Exam, HLE)'**을 개발했습니다.
2700개의 질문, 인간 지식의 경계를 넘어서
HLE는 수학, 인문학, 자연과학 등 수십 개 분야에 걸쳐 2700개의 질문으로 구성되어 있습니다. 단순히 암기식 지식이 아닌, 깊이 있는 이해와 응용력을 요구하는 다중 모드 벤치마크로 기획되었으며, 자동 채점이 가능하도록 객관식 및 단답형 질문으로 구성되어 있습니다. 각 질문은 명확하고 검증 가능한 답을 가지고 있지만, 인터넷 검색으로는 쉽게 찾을 수 없도록 설계되었습니다. 이는 단순히 정보 습득 능력이 아닌, 진정한 이해와 사고 능력을 평가하는 데 초점을 맞춘 것입니다.
최첨단 LLM도 쩔쩔매는 도전 과제
흥미롭게도, 최첨단 LLM조차 HLE에서 낮은 정확도와 보정 능력을 보였습니다. 이는 현재 LLM의 능력이 인간 전문가의 수준에 미치지 못함을 시사합니다. HLE는 단순한 벤치마크를 넘어, AI의 현주소를 정확하게 파악하고 미래 연구 방향을 제시하는 중요한 이정표가 될 것입니다.
공개된 HLE: AI 연구 및 정책 수립의 촉매제
'인류의 마지막 시험' 벤치마크는 https://lastexam.ai 에서 공개되어 있으며, AI 연구자, 정책 입안자들에게 모델의 능력에 대한 명확한 이해를 제공하고, 더욱 발전된 AI 시스템 개발을 위한 귀중한 정보를 제공할 것으로 기대됩니다. 이는 AI 기술 발전에 대한 객관적인 평가와 윤리적인 고려를 동시에 가능하게 하는 중요한 단계입니다. 앞으로 HLE가 AI 연구와 발전에 어떤 영향을 미칠지, 그리고 인간과 AI의 공존에 대한 새로운 패러다임을 제시할지 주목할 만합니다. 🎉
Reference
[arxiv] Humanity's Last Exam
Published: (Updated: )
Author: Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, Michael Choi, Anish Agrawal, Arnav Chopra, Adam Khoja, Ryan Kim, Richard Ren, Jason Hausenloy, Oliver Zhang, Mantas Mazeika, Tung Nguyen, Daron Anderson, Imad Ali Shah, Mikhail Doroshenko, Alun Cennyth Stokes, Mobeen Mahmood, Jaeho Lee, Oleksandr Pokutnyi, Oleg Iskra, Jessica P. Wang, Robert Gerbicz, John-Clark Levin, Serguei Popov, Fiona Feng, Steven Y. Feng, Haoran Zhao, Michael Yu, Varun Gangal, Chelsea Zou, Zihan Wang, Mstyslav Kazakov, Geoff Galgon, Johannes Schmitt, Alvaro Sanchez, Yongki Lee, Will Yeadon, Scott Sauers, Marc Roth, Chidozie Agu, Søren Riis, Fabian Giska, Saiteja Utpala, Antrell Cheatom, Zachary Giboney, Gashaw M. Goshu, Sarah-Jane Crowson, Mohinder Maheshbhai Naiya, Noah Burns, Lennart Finke, Zerui Cheng, Hyunwoo Park, Francesco Fournier-Facio, Jennifer Zampese, John B. Wydallis, Ryan G. Hoerr, Mark Nandor, Tim Gehrunger, Jiaqi Cai, Ben McCarty, Jungbae Nam, Edwin Taylor, Jun Jin, Gautier Abou Loume, Hangrui Cao, Alexis C Garretson, Damien Sileo, Qiuyu Ren, Doru Cojoc, Pavel Arkhipov, Usman Qazi, Aras Bacho, Lianghui Li, Sumeet Motwani, Christian Schroeder de Witt, Alexei Kopylov, Johannes Veith, Eric Singer, Paolo Rissone, Jaehyeok Jin, Jack Wei Lun Shi, Chris G. Willcocks, Ameya Prabhu, Longke Tang, Kevin Zhou, Emily de Oliveira Santos, Andrey Pupasov Maksimov, Edward Vendrow, Kengo Zenitani, Joshua Robinson, Aleksandar Mikov, Julien Guillod, Yuqi Li, Ben Pageler, Joshua Vendrow, Vladyslav Kuchkin, Pierre Marion, Denis Efremov, Jayson Lynch, Kaiqu Liang, Andrew Gritsevskiy, Dakotah Martinez, Nick Crispino, Dimitri Zvonkine, Natanael Wildner Fraga, Saeed Soori, Ori Press, Henry Tang, Julian Salazar, Sean R. Green, Lina Brüssel, Moon Twayana, Aymeric Dieuleveut, T. Ryan Rogers, Wenjin Zhang, Ross Finocchio, Bikun Li, Jinzhou Yang, Arun Rao, Gabriel Loiseau, Mikhail Kalinin, Marco Lukas, Ciprian Manolescu, Nate Stambaugh, Subrata Mishra, Ariel Ghislain Kemogne Kamdoum, Tad Hogg, Alvin Jin, Carlo Bosio, Gongbo Sun, Brian P Coppola, Haline Heidinger, Rafael Sayous, Stefan Ivanov, Joseph M Cavanagh, Jiawei Shen, Joseph Marvin Imperial, Philippe Schwaller, Shaipranesh Senthilkuma, Andres M Bran, Andres Algaba, Brecht Verbeken, Kelsey Van den Houte, Lynn Van Der Sypt, David Noever, Lisa Schut, Ilia Sucholutsky, Evgenii Zheltonozhskii, Qiaochu Yuan, Derek Lim, Richard Stanley, Shankar Sivarajan, Tong Yang, John Maar, Julian Wykowski, Martí Oller, Jennifer Sandlin, Anmol Sahu, Cesare Giulio Ardito, Yuzheng Hu, Felipe Meneguitti Dias, Tobias Kreiman, Kaivalya Rawal, Tobias Garcia Vilchis, Yuexuan Zu, Martin Lackner, James Koppel, Jeremy Nguyen, Daniil S. Antonenko, Steffi Chern, Bingchen Zhao, Pierrot Arsene, Sergey Ivanov, Rafał Poświata, Chenguang Wang, Daofeng Li, Donato Crisostomi, Ali Dehghan, Andrea Achilleos, John Arnold Ambay, Benjamin Myklebust, Archan Sen, David Perrella, Nurdin Kaparov, Mark H Inlow, Allen Zang, Kalyan Ramakrishnan, Daniil Orel, Vladislav Poritski, Shalev Ben-David, Zachary Berger, Parker Whitfill, Michael Foster, Daniel Munro, Linh Ho, Dan Bar Hava, Aleksey Kuchkin, Robert Lauff, David Holmes, Frank Sommerhage, Anji Zhang, Richard Moat, Keith Schneider, Daniel Pyda, Zakayo Kazibwe, Mukhwinder Singh, Don Clarke, Dae Hyun Kim, Sara Fish, Veit Elser, Victor Efren Guadarrama Vilchis, Immo Klose, Christoph Demian, Ujjwala Anantheswaran, Adam Zweiger, Guglielmo Albani, Jeffery Li, Nicolas Daans, Maksim Radionov, Václav Rozhoň, Vincent Ginis, Ziqiao Ma, Christian Stump, Jacob Platnick, Volodymyr Nevirkovets, Luke Basler, Marco Piccardo, Niv Cohen, Virendra Singh, Josef Tkadlec, Paul Rosu, Alan Goldfarb, Piotr Padlewski, Stanislaw Barzowski, Kyle Montgomery, Aline Menezes, Arkil Patel, Zixuan Wang, Jamie Tucker-Foltz, Jack Stade, Declan Grabb, Tom Goertzen, Fereshteh Kazemi, Jeremiah Milbauer, Abhishek Shukla, Hossam Elgnainy, Yan Carlos Leyva Labrador, Hao He, Ling Zhang, Alan Givré, Hew Wolff, Gözdenur Demir, Muhammad Fayez Aziz, Younesse Kaddar, Ivar Ängquist, Yanxu Chen, Elliott Thornley, Robin Zhang, Jiayi Pan, Antonio Terpin, Niklas Muennighoff, Hailey Schoelkopf, Eric Zheng, Avishy Carmi, Jainam Shah, Ethan D. L. Brown, Kelin Zhu, Max Bartolo, Richard Wheeler, Andrew Ho, Shaul Barkan, Jiaqi Wang, Martin Stehberger, Egor Kretov, Peter Bradshaw, JP Heimonen, Kaustubh Sridhar, Zaki Hossain, Ido Akov, Yury Makarychev, Joanna Tam, Hieu Hoang, David M. Cunningham, Vladimir Goryachev, Demosthenes Patramanis, Michael Krause, Andrew Redenti, David Aldous, Jesyin Lai, Shannon Coleman, Jiangnan Xu, Sangwon Lee, Ilias Magoulas, Sandy Zhao, Ning Tang, Michael K. Cohen, Micah Carroll, Orr Paradise, Jan Hendrik Kirchner, Stefan Steinerberger, Maksym Ovchynnikov, Jason O. Matos, Adithya Shenoy, Michael Wang, Yuzhou Nie, Paolo Giordano, Philipp Petersen, Anna Sztyber-Betley, Paolo Faraboschi, Robin Riblet, Jonathan Crozier, Shiv Halasyamani, Antonella Pinto, Shreyas Verma, Prashant Joshi, Eli Meril, Zheng-Xin Yong, Allison Tee, Jérémy Andréoletti, Orion Weller, Raghav Singhal, Gang Zhang, Alexander Ivanov, Seri Khoury, Nils Gustafsson, Hamid Mostaghimi, Kunvar Thaman, Qijia Chen, Tran Quoc Khánh, Jacob Loader, Stefano Cavalleri, Hannah Szlyk, Zachary Brown, Himanshu Narayan, Jonathan Roberts, William Alley, Kunyang Sun, Ryan Stendall, Max Lamparth, Anka Reuel, Ting Wang, Hanmeng Xu, Pablo Hernández-Cámara, Freddie Martin, Thomas Preu, Tomek Korbak, Marcus Abramovitch, Dominic Williamson, Ida Bosio, Ziye Chen, Biró Bálint, Eve J. Y. Lo, Maria Inês S. Nunes, Yibo Jiang, M Saiful Bari, Peyman Kassani, Zihao Wang, Behzad Ansarinejad, Yewen Sun, Stephane Durand, Guillaume Douville, Daniel Tordera, George Balabanian, Earth Anderson, Lynna Kvistad, Alejandro José Moyano, Hsiaoyun Milliron, Ahmad Sakor, Murat Eron, Isaac C. McAlister, Andrew Favre D. O., Shailesh Shah, Xiaoxiang Zhou, Firuz Kamalov, Ronald Clark, Sherwin Abdoli, Tim Santens, Harrison K Wang, Evan Chen, Alessandro Tomasiello, G. Bruno De Luca, Shi-Zhuo Looi, Vinh-Kha Le, Noam Kolt, Niels Mündler, Avi Semler, Emma Rodman, Jacob Drori, Carl J Fossum, Luk Gloor, Milind Jagota, Ronak Pradeep, Honglu Fan, Tej Shah, Jonathan Eicher, Michael Chen, Kushal Thaman, William Merrill, Moritz Firsching, Carter Harris, Stefan Ciobâcă, Jason Gross, Rohan Pandey, Ilya Gusev, Adam Jones, Shashank Agnihotri, Pavel Zhelnov, Siranut Usawasutsakorn, Mohammadreza Mofayezi, Alexander Piperski, Marc Carauleanu, David K. Zhang, Kostiantyn Dobarskyi, Dylan Ler, Roman Leventov, Ignat Soroko, Thorben Jansen, Scott Creighton, Pascal Lauer, Joshua Duersch, Vage Taamazyan, Dario Bezzi, Wiktor Morak, Wenjie Ma, William Held, Tran Đuc Huy, Ruicheng Xian, Armel Randy Zebaze, Mohanad Mohamed, Julian Noah Leser, Michelle X Yuan, Laila Yacar, Johannes Lengler, Katarzyna Olszewska, Hossein Shahrtash, Edson Oliveira, Joseph W. Jackson, Daniel Espinosa Gonzalez, Andy Zou, Muthu Chidambaram, Timothy Manik, Hector Haffenden, Dashiell Stander, Ali Dasouqi, Alexander Shen, Emilien Duc, Bita Golshani, David Stap, Mikalai Uzhou, Alina Borisovna Zhidkovskaya, Lukas Lewark, Miguel Orbegozo Rodriguez, Mátyás Vincze, Dustin Wehr, Colin Tang, Shaun Phillips, Fortuna Samuele, Jiang Muzhen, Fredrik Ekström, Angela Hammon, Oam Patel, Faraz Farhidi, George Medley, Forough Mohammadzadeh, Madellene Peñaflor, Haile Kassahun, Alena Friedrich, Claire Sparrow, Rayner Hernandez Perez, Taom Sakal, Omkar Dhamane, Ali Khajegili Mirabadi, Eric Hallman, Kenchi Okutsu, Mike Battaglia, Mohammad Maghsoudimehrabani, Alon Amit, Dave Hulbert, Roberto Pereira, Simon Weber, Handoko, Anton Peristyy, Stephen Malina, Samuel Albanie, Will Cai, Mustafa Mehkary, Rami Aly, Frank Reidegeld, Anna-Katharina Dick, Cary Friday, Jasdeep Sidhu, Hassan Shapourian, Wanyoung Kim, Mariana Costa, Hubeyb Gurdogan, Brian Weber, Harsh Kumar, Tong Jiang, Arunim Agarwal, Chiara Ceconello, Warren S. Vaz, Chao Zhuang, Haon Park, Andrew R. Tawfeek, Daattavya Aggarwal, Michael Kirchhof, Linjie Dai, Evan Kim, Johan Ferret, Yuzhou Wang, Minghao Yan, Krzysztof Burdzy, Lixin Zhang, Antonio Franca, Diana T. Pham, Kang Yong Loh, Joshua Robinson, Abram Jackson, Shreen Gul, Gunjan Chhablani, Zhehang Du, Adrian Cosma, Jesus Colino, Colin White, Jacob Votava, Vladimir Vinnikov, Ethan Delaney, Petr Spelda, Vit Stritecky, Syed M. Shahid, Jean-Christophe Mourrat, Lavr Vetoshkin, Koen Sponselee, Renas Bacho, Florencia de la Rosa, Xiuyu Li, Guillaume Malod, Leon Lang, Julien Laurendeau, Dmitry Kazakov, Fatimah Adesanya, Julien Portier, Lawrence Hollom, Victor Souza, Yuchen Anna Zhou, Julien Degorre, Yiğit Yalın, Gbenga Daniel Obikoya, Luca Arnaboldi, Rai, Filippo Bigi, M. C. Boscá, Oleg Shumar, Kaniuar Bacho, Pierre Clavier, Gabriel Recchia, Mara Popescu, Nikita Shulga, Ngefor Mildred Tanwie, Denis Peskoff, Thomas C. H. Lux, Ben Rank, Colin Ni, Matthew Brooks, Alesia Yakimchyk, Huanxu, Liu, Olle Häggström, Emil Verkama, Hans Gundlach, Leonor Brito-Santana, Brian Amaro, Vivek Vajipey, Rynaa Grover, Yiyang Fan, Gabriel Poesia Reis e Silva, Linwei Xin, Yosi Kratish, Jakub Łucki, Wen-Ding Li, Sivakanth Gopi, Andrea Caciolai, Justin Xu, Kevin Joseph Scaria, Freddie Vargus, Farzad Habibi, Long, Lian, Emanuele Rodolà, Jules Robins, Vincent Cheng, Tony Fruhauff, Brad Raynor, Hao Qi, Xi Jiang, Ben Segev, Jingxuan Fan, Sarah Martinson, Erik Y. Wang, Kaylie Hausknecht, Michael P. Brenner, Mao Mao, Xinyu Zhang, David Avagian, Eshawn Jessica Scipio, Alon Ragoler, Justin Tan, Blake Sims, Rebeka Plecnik, Aaron Kirtland, Omer Faruk Bodur, D. P. Shinde, Zahra Adoul, Mohamed Zekry, Ali Karakoc, Tania C. B. Santos, Samir Shamseldeen, Loukmane Karim, Anna Liakhovitskaia, Nate Resman, Nicholas Farina, Juan Carlos Gonzalez, Gabe Maayan, Sarah Hoback, Rodrigo De Oliveira Pena, Glen Sherman, Elizabeth Kelley, Hodjat Mariji, Rasoul Pouriamanesh, Wentao Wu, Sandra Mendoza, Ismail Alarab, Joshua Cole, Danyelle Ferreira, Bryan Johnson, Mohammad Safdari, Liangti Dai, Siriphan Arthornthurasuk, Alexey Pronin, Jing Fan, Angel Ramirez-Trinidad, Ashley Cartwright, Daphiny Pottmaier, Omid Taheri, David Outevsky, Stanley Stepanic, Samuel Perry, Luke Askew, Raúl Adrián Huerta Rodríguez, Ali M. R. Minissi, Sam Ali, Ricardo Lorena, Krishnamurthy Iyer, Arshad Anil Fasiludeen, Sk Md Salauddin, Murat Islam, Juan Gonzalez, Josh Ducey, Maja Somrak, Vasilios Mavroudis, Eric Vergo, Juehang Qin, Benjámin Borbás, Eric Chu, Jack Lindsey, Anil Radhakrishnan, Antoine Jallon, I. M. J. McInnis, Pawan Kumar, Laxman Prasad Goswami, Daniel Bugas, Nasser Heydari, Ferenc Jeanplong, Archimedes Apronti, Abdallah Galal, Ng Ze-An, Ankit Singh, Joan of Arc Xavier, Kanu Priya Agarwal, Mohammed Berkani, Benedito Alves de Oliveira Junior, Dmitry Malishev, Nicolas Remy, Taylor D. Hartman, Tim Tarver, Stephen Mensah, Javier Gimenez, Roselynn Grace Montecillo, Russell Campbell, Asankhaya Sharma, Khalida Meer, Xavier Alapont, Deepakkumar Patil, Rajat Maheshwari, Abdelkader Dendane, Priti Shukla, Sergei Bogdanov, Sören Möller, Muhammad Rehan Siddiqi, Prajvi Saxena, Himanshu Gupta, Innocent Enyekwe, Ragavendran P V, Zienab EL-Wasif, Aleksandr Maksapetyan, Vivien Rossbach, Chris Harjadi, Mohsen Bahaloohoreh, Song Bian, John Lai, Justine Leon Uro, Greg Bateman, Mohamed Sayed, Ahmed Menshawy, Darling Duclosel, Yashaswini Jain, Ashley Aaron, Murat Tiryakioglu, Sheeshram Siddh, Keith Krenek, Alex Hoover, Joseph McGowan, Tejal Patwardhan, Summer Yue, Alexandr Wang, Dan Hendrycks
http://arxiv.org/abs/2501.14249v5