Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Research community dynamics behind popular AI benchmarks


The widespread use of experimental benchmarks in AI research has created competition and collaboration dynamics that are still poorly understood. Here we provide an innovative methodology to explore these dynamics and analyse the way different entrants in these challenges, from academia to tech giants, behave and react depending on their own or others’ achievements. We perform an analysis of 25 popular benchmarks in AI from Papers With Code, with around 2,000 result entries overall, connected with their underlying research papers. We identify links between researchers and institutions (that is, communities) beyond the standard co-authorship relations, and we explore a series of hypotheses about their behaviour as well as some aggregated results in terms of activity, performance jumps and efficiency. We characterize the dynamics of research communities at different levels of abstraction, including organization, affiliation, trajectories, results and activity. We find that hybrid, multi-institution and persevering communities are more likely to improve state-of-the-art performance, which becomes a watershed for many community members. Although the results cannot be extrapolated beyond our selection of popular machine learning benchmarks, the methodology can be extended to other areas of artificial intelligence or robotics, and combined with bibliometric studies.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Progress in accuracy over time for ImageNet.
Fig. 2: Progress in accuracy over time for SQuAD1.1.
Fig. 3: Most prolific institutions (at least ten entries) in terms of total SOTA jumps entries and activity.

Data availability

The data regarding all the papers analysed, their authors, community memberships, results for the different benchmarks and SOTA jumps can be found in the data folder on GitHub41 (‘data’ folder).

Code availability

The code for reproducing results can be found on GitHub41.


  1. Fortunato, S. et al. Science of science. Science 359, eaao0185 (2018).

    Article  Google Scholar 

  2. Wu, L., Wang, D. & Evans, J. A. Large teams develop and small teams disrupt science and technology. Nature 566, 378–382 (2019).

    Article  Google Scholar 

  3. Frank, M. R., Wang, D., Cebrian, M. & Rahwan, I. The evolution of citation graphs in artificial intelligence research. Nat. Mach. Intell. 1, 79–85 (2019).

    Article  Google Scholar 

  4. Martínez-Plumed, F. et al. Accounting for the neglected dimensions of AI progress. Preprint at (2018).

  5. Perrault, R. et al. The AI Index 2019 Annual Report (AI Index Steering Committee, Human-Centered AI Institute, Stanford Univ. 2019);

  6. Clauset, A., Newman, M. E. J. & Moore, C. Finding community structure in very large networks. Phys. Rev. E 70, 66–111 (2004).

    Article  Google Scholar 

  7. Van Raan, A. The influence of international collaboration on the impact of research results: some simple mathematical considerations concerning the role of self-citations. Scientometrics 42, 423–428 (1998).

    Article  Google Scholar 

  8. Deng, J. et al. ImageNet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition 248–55 (IEEE, 2009).

  9. Rajpurkar, P., Zhang, J., Lopyrev, K. & Liang, P. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing 2383–2392 (Association for Computational Linguistics, 2016).

  10. Bonferroni, C. Teoria statistica delle classi e calcolo delle probabilita. Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze 8, 3–62 (1936).

    MATH  Google Scholar 

  11. Kwok, R. Junior AI researchers are in demand by universities and industry. Nature 568, 581–584 (2019).

    Article  Google Scholar 

  12. Rhoades, S. A. The Herfindahl–Hirschman index. Fed. Res. Bull. 79, 188–189 (1993).

    Google Scholar 

  13. Cave, S. & Ó hÉigeartaigh, S. S. An AI race for strategic advantage: rhetoric and risks. In Proc. 2018 AAAI/ACM Conference on AI, Ethics, and Society 36–40 (Association for Computing Machinery, 2018).

  14. Lee, K.-F. AI Superpowers: China, Silicon Valley, and the New World Order (Houghton Mifflin Harcourt, 2018).

  15. Horowitz, M. C., Allen, G. C., Kania, E. B. & Scharre, P. Strategic Competition in an Era of Artificial Intelligence 8 (Center for New American Security, 2018).

  16. Li, W. C., Nirei, M. & Yamana, K. Value of Data: There’s No Such Thing as a Free Lunch in the Digital Economy Working Paper (US Bureau of Economic Analysis, 2019).

  17. Krizhevsky, A. Learning Multiple Layers of Features from Tiny Images. (2009).

  18. Hernández-Orallo, J. et al. A new AI evaluation cosmos: Ready to play the game? AI Magazine 38, 66–69 (2017).

    Article  Google Scholar 

  19. Shoham, Y. Towards the AI index. AI Magazine 38, 71–77 (2017).

    Article  Google Scholar 

  20. Niu, J., Tang, W., Xu, F., Zhou, X. & Song, Y. Global research on AI from 1990–2014: spatially-explicit bibliometric analysis. ISPRS Int. J. Geoinf. 5, 66 (2016).

    Article  Google Scholar 

  21. Juan Mateos-Garcia, K. S., Klinger, J. & Winch, R. A Semantic Analysis of the Recent Evolution of AI Research. (NESTA, 2019).

  22. Gao, F. et al. Bibliometric analysis on tendency and topics of artificial intelligence over last decade. Microsyst. Technol. 1–13 (2019).

  23. Tran, B. X. et al. Global evolution of research in artificial intelligence in health and medicine: a bibliometric study. J. Clin. Med. 8, 360 (2019).

    Article  Google Scholar 

  24. Tang, X., Li, X., Ding, Y., Song, M. & Bu, Y. The pace of artificial intelligence innovations: speed, talent, and trial-and-error. J. Inf. 14, 101094 (2020).

    Google Scholar 

  25. Qian, Y., Liu, Y. & Sheng, Q. Z. Understanding hierarchical structural evolution in a scientific discipline: a case study of artificial intelligence. J. Inf. 14, 101047 (2020).

    Google Scholar 

  26. Serenko, A. The development of an AI journal ranking based on the revealed preference approach. J. Inf. 4, 447–459 (2010).

    Google Scholar 

  27. Campbell, M., Hoane Jr, A. J. & Hsu, F.-h Deep Blue. Artif. Intell. 134, 57–83 (2002).

    Article  Google Scholar 

  28. Ferrucci, D. A. Introduction to ‘This is Watson’. IBM J. Res. Dev. 56, 235–249 (2012).

    Article  Google Scholar 

  29. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).

    Article  Google Scholar 

  30. Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–489 (2016).

    Article  Google Scholar 

  31. Schlangen, D. Language tasks and language games: on methodology in current natural language processing research. Preprint at (2019).

  32. Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A. & Choi, Y. Hellaswag: can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 4791–4800 (Association for Computational Linguistics, 2019).

  33. Lei, Y. & Liu, Z. The development of artificial intelligence: a bibliometric analysis, 2007–2016. J. Physi. 1168, 022027 (2019).

  34. Martínez-Plumed, F. et al. The facets of artificial intelligence: a framework to track the evolution of AI. In Proc. Twenty-Seventh International Joint Conference on Artificial Intelligence 5180–5187 (International Joint Conferences on Artificial Intelligence Organization, 2018).

  35. Bhattacharya, J. & Packalen, M. Stagnation and Scientific Incentives Technical Report (National Bureau of Economic Research, 2020).

  36. Houghton, B. et al. Guaranteeing reproducibility in deep learning competitions. Preprint at (2020).

  37. Lucic, M., Kurach, K., Michalski, M., Gelly, S. & Bousquet, O. Are gans created equal? A large-scale study. Adv. Neural Inf. Process. Syst. 700–709 (2018).

  38. Hernandez, D. & Brown, T. B. Measuring the algorithmic efficiency of neural networks. Preprint at (2020).

  39. Mattson, P. et al. MLPerf training benchmark. Preprint (2019).

  40. Martínez-Plumed, F. & Hernández-Orallo, J. Dual indicators to analyse AI benchmarks: difficulty, discrimination, ability, and generality. IEEE Trans. Games 12, 121–131 (2020).

    Article  Google Scholar 

  41. Martínez-Plumed, F., Barredo, P., hÉigeartaigh, S. Ó. & Hernández-Orallo, J. AI research dynamics. GitHub (2021).

  42. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T. & Serre, T. HMDB: a large video database for human motion recognition. In 2011 International Conference on Computer Vision 2556–2563 (IEEE, 2011).

  43. Soomro, K., Zamir, A. R. & Shah, M. UCF101: a dataset of 101 human actions classes from videos in the wild. Preprint at (2012).

  44. Bellemare, M. G., Naddaf, Y., Veness, J. & Bowling, M. The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–279 (2013).

    Article  Google Scholar 

  45. Timofte, R., De Smet, V. & Van Gool, L. Anchored neighborhood regression for fast example-based super-resolution. In Proc. IEEE International Conference on Computer Vision 1920–1927 (IEEE, 2013).

  46. Hutter, M. Human knowledge compression contest. Hutter Prize (2006).

  47. Mikolov, T., Deoras, A., Kombrink, S., Burget, L. & Černocky, J. Empirical evaluation and combination of advanced language modeling techniques. In Twelfth Annual Conference of the International Speech Communication Association 605–608 (2011).

  48. Dettmers, T., Minervini, P., Stenetorp, P. & Riedel, S. Convolutional 2D knowledge graph embeddings. In Proc. AAAI Conference on Artificial Intelligence Vol. 32 (2018).

  49. Bojar, O. et al. Findings of the 2014 workshop on statistical machine translation. In Proc. Ninth Workshop on Statistical Machine Translation 12–58 (Association for Computational Linguistics, 2014);

  50. Sang, E. F. & De Meulder, F. Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003 142–147 (2003).

  51. Weischedel, R. et al. Ontonotes Release 5.0 ldc2013t19 23 (Linguistic Data Consortium, 2013).

  52. Lin, T.-Y. et al. Microsoft COCO: common objects in context. In European Conference on Computer Vision 740–755 (Springer, 2014).

  53. Andriluka, M., Pishchulin, L., Gehler, P. & Schiele, B. 2D human pose estimation: new benchmark and state of the art analysis. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 3686–3693 (IEEE, 2014).

  54. Yang, Y., Yih, W.-t. & Meek, C. Wikiqa: a challenge dataset for open-domain question answering. In Proc. 2015 Conference on Empirical Methods in Natural Language Processing 2013–2018 (Association for Computational Linguistics, 2015).

  55. Cordts, M. et al. The cityscapes dataset for semantic urban scene understanding. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 3213–3223 (IEEE, 2016).

  56. Everingham, M. et al. The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98–136 (2015).

    Article  Google Scholar 

  57. Maas, A. L. et al. Learning word vectors for sentiment analysis. In Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies Vol. 1, 142–150 (Association for Computational Linguistics, 2011).

  58. Socher, R. et al. Recursive deep models for semantic compositionality over a sentiment treebank. In Proc. 2013 Conference on Empirical Methods in Natural Language Processing 1631–1642 (Association for Computational Linguistics, 2013).

  59. Panayotov, V., Chen, G., Povey, D. & Khudanpur, S. Librispeech: an ASR corpus based on public domain audio books. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 5206–5210 (IEEE, 2015).

Download references


F.M.-P. acknowledges funding from the AI-Watch project by DG CONNECT and DG JRC of the European Commission. J.H.-O. and S.Ó.h. were funded by the Future of Life Institute, FLI, under grant RFP2-152. J.H.-O. was supported by the EU (FEDER) and Spanish MINECO under RTI2018-094403-B-C32, Generalitat Valenciana under PROMETEO/2019/098 and European Union’s Horizon 2020 grant no. 952215 (TAILOR).

Author information

Authors and Affiliations



The four authors, F.M.-P., P.B., S.Ó.h. and J.H.-O., participated in the definition and refinement of the goals of this study and the hypotheses. F.M.-P., J.H.-O. and P.B. conceived the technical methodology. P.B. and F.M.-P. implemented the code that collects and processes the data, and creates the communities. F.M.-P. generated the plots. All authors discussed the results and contributed to the writing of the final manuscript.

Corresponding authors

Correspondence to Fernando Martínez-Plumed, Pablo Barredo, Seán Ó hÉigeartaigh or José Hernández-Orallo.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review informationNature Machine Intelligence thanks Nima Dehmamy, Lars Kotthoff and Dashun Wang for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary analysis, Figs. 1–26 and Table 1.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Martínez-Plumed, F., Barredo, P., hÉigeartaigh, S.Ó. et al. Research community dynamics behind popular AI benchmarks. Nat Mach Intell 3, 581–589 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing