{"work":{"id":"54fdcd2d-ade5-4d5e-9b37-8d75abcbaae2","openalex_id":null,"doi":null,"arxiv_id":"1905.00537","raw_key":null,"title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","authors":null,"authors_text":"Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill","year":2019,"venue":"cs.CL","abstract":"In the last year, new models and methods for pretraining and transfer learning have driven striking performance improvements across a range of language understanding tasks. The GLUE benchmark, introduced a little over one year ago, offers a single-number metric that summarizes progress on a diverse set of such tasks, but performance on the benchmark has recently surpassed the level of non-expert humans, suggesting limited headroom for further research. In this paper we present SuperGLUE, a new benchmark styled after GLUE with a new set of more difficult language understanding tasks, a software toolkit, and a public leaderboard. SuperGLUE is available at super.gluebenchmark.com.","external_url":"https://arxiv.org/abs/1905.00537","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-16T14:48:08.707319+00:00","pith_arxiv_id":"1905.00537","created_at":"2026-05-09T04:47:44.476049+00:00","updated_at":"2026-05-16T14:48:08.707319+00:00","title_quality_ok":true,"display_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","render_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems"},"hub":{"state":{"work_id":"54fdcd2d-ade5-4d5e-9b37-8d75abcbaae2","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2019-07-26T17:48:29+00:00","last_pith_cited_at":"2026-05-13T19:25:56+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-17T18:20:01.922607+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}