Datasets › RACE

RACE (ReAding Comprehension dataset from Examinations)

Introduced by Guokun Lai et al. in RACE: Large-scale ReAding Comprehension Dataset From Examinations1 Jan 2017 archive 2025-07-28

The ReAding Comprehension dataset from Examinations (RACE) dataset is a machine reading comprehension dataset consisting of 27,933 passages and 97,867 questions from English exams, targeting Chinese students aged 12-18. RACE consists of two subsets, RACE-M and RACE-H, from middle school and high school exams, respectively. RACE-M has 28,293 questions and RACE-H has 69,574. Each question is associated with 4 candidate answers, one of which is correct. The data generation process of RACE differs from most machine reading comprehension datasets - instead of generating questions and answers by heuristics or crowd-sourcing, questions in RACE are specifically designed for testing human reading skills, and are created by domain experts.

Source: Dynamic Fusion Networks for Machine Reading Comprehension Image Source: Lai et al

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 6 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Reading Comprehension · RACE (3 judged, 0 placed), Question Answering · RACE (3 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

Papers archive 2025-07-28

papers with a benchmark row: 18 · with a code link: 12 · where Syntology ran a sample: 8 (8 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (8 of 18 with a benchmark row: 8 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 18 of 18 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 412. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Orca 2: Teaching Small Language Models How to Reason 0 2 18 Nov 2023 not harvested
BloombergGPT: A Large Language Model for Finance 2 4 30 Mar 2023 not harvested
LLaMA: Open and Efficient Foundation Language Models 57 4 27 Feb 2023 official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified (4 pointer-only for licence)
PaLM: Scaling Language Modeling with Pathways 7 3 5 Apr 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified
Hierarchical Learning for Generation with Long Source Sequences 0 1 15 Apr 2021 not harvested
Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning 0 1 6 Nov 2020 not harvested
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies 1 1 12 Oct 2020 not harvested
DeBERTa: Decoding-enhanced BERT with Disentangled Attention 14 1 5 Jun 2020 official: no sample here; runs from other or unrecorded repositories · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified (3 pointer-only for licence)
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing 3 1 5 Jun 2020 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Language Models are Few-Shot Learners 67 4 28 May 2020 community repositories only · 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified (7 pointer-only for licence)
DUMA: Reading Comprehension with Transposition Thinking 3 1 26 Jan 2020 not harvested
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism 10 2 17 Sep 2019 community repositories only · 12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified (15 pointer-only for licence)
RoBERTa: A Robustly Optimized BERT Pretraining Approach 67 1 26 Jul 2019 community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified (24 pointer-only for licence)
XLNet: Generalized Autoregressive Pretraining for Language Understanding 27 2 19 Jun 2019 official (archive's flag): 1 ran · 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified (4 pointer-only for licence)
Option Comparison Network for Multiple-choice Reading Comprehension 0 1 7 Mar 2019 not harvested
Dual Co-Matching Network for Multi-choice Reading Comprehension 0 1 27 Jan 2019 not harvested
Improving Language Understanding by Generative Pre-Training 13 1 11 Jun 2018 not harvested
Multi-range Reasoning for Machine Comprehension 0 1 24 Mar 2018 not harvested

Dataset loaders archive 2025-07-28

7 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom (research-only, non-commercial)

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • RACE

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections