OpenCodePapers

multi-task-language-understanding-on-mgsm

Multi-Task LearningMulti-task Language Understanding
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAverage (%)ModelNameReleaseDate
PaLM 2 Technical Report✓ Link87.0PaLM 2 (few-shot, k=8, SC)2023-05-17
PaLM 2 Technical Report✓ Link72.2PaLM 2 (8-shot, CoT)2023-05-17
Scaling Instruction-Finetuned Language Models✓ Link72.0Flan-PaLM 540B (8-shot, fine-tuned, CoT + SC)2022-10-20
Scaling Instruction-Finetuned Language Models✓ Link60.4Flan-U-PaLM 540B (CoT)2022-10-20
Scaling Instruction-Finetuned Language Models✓ Link57.0Flan-PaLM 540B (8-shot, fine-tuned, CoT)2022-10-20
PaLM: Scaling Language Modeling with Pathways✓ Link55.0PaLM 540B2022-04-05
Transcending Scaling Laws with 0.1% Extra Compute49.9U-PaLM 540B (CoT)2022-10-20
Scaling Instruction-Finetuned Language Models✓ Link36text-davinci-0032022-10-20
Scaling Instruction-Finetuned Language Models✓ Link35code-davinci-0022022-10-20
Scaling Instruction-Finetuned Language Models✓ Link23.7text-davinci-0022022-10-20
Scaling Instruction-Finetuned Language Models✓ Link21.2Flan-PaLM 540B (8-shot, fine-tuned)2022-10-20
Scaling Instruction-Finetuned Language Models✓ Link5.7GPT-3 Davinci 175B2022-10-20