ML Research Wiki / Benchmarks / Question Answering / RACE

RACE

Question Answering Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: RACE-m

Top Performing Models

Rank Model Paper RACE-m Date Code
1 XLNet XLNet: Generalized Autoregressive Pretraining for Language Understanding 85.45 2019-06-19 📦 huggingface/transformers 📦 PaddlePaddle/PaddleNLP 📦 zihangdai/xlnet
2 OCN_large Option Comparison Network for Multiple-choice Reading Comprehension 76.70 2019-03-07 -
3 DCMN_large Dual Co-Matching Network for Multi-choice Reading Comprehension 73.40 2019-01-27 -
4 BiAttention MRU Multi-range Reasoning for Machine Comprehension 60.20 2018-03-24 -
5 GPT-3 175B (few-shot, k=32) Language Models are Few-Shot Learners 58.10 2020-05-28 📦 ggml-org/llama.cpp 📦 ggerganov/llama.cpp 📦 karpathy/llm.c
6 GPT-3 175B (Few-Shot) Language Models are Few-Shot Learners 46.80 2020-05-28 📦 ggml-org/llama.cpp 📦 ggerganov/llama.cpp 📦 karpathy/llm.c

All Papers (6)

huggingface/transformers PaddlePaddle/PaddleNLP

Language Models are Few-Shot Learners

2020
GPT-3 175B (few-shot, k=32)
ggml-org/llama.cpp ggerganov/llama.cpp

Language Models are Few-Shot Learners

2020
GPT-3 175B (Few-Shot)
ggml-org/llama.cpp ggerganov/llama.cpp