SOTAVerified

General Knowledge

This task aims to evaluate the ability of a model to answer general-knowledge questions.

Source: BIG-bench

Papers

Showing 391399 of 399 papers

TitleStatusHype
REFinD: Relation Extraction Financial DatasetCode0
Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov LogicCode0
Exploiting Adapters for Cross-lingual Low-resource Speech RecognitionCode0
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference ContentCode0
Towards Knowledge-Augmented Visual Question AnsweringCode0
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist ExaminationCode0
Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge GraphCode0
DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning ApproachCode0
Survey on Abstractive Text Summarization: Dataset, Models, and MetricsCode0
Show:102550
← PrevPage 40 of 40Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Chinchilla-70B (few-shot, k=5)Accuracy94.3Unverified
2Gopher-280B (few-shot, k=5)Accuracy93.9Unverified
3Chinchilla-70B (few-shot, k=5)Accuracy 85.7Unverified
4Gopher-280B (few-shot, k=5)Accuracy 84.8Unverified
5Gopher-280B (few-shot, k=5)Accuracy84.2Unverified
6Gopher-280B (few-shot, k=5)Accuracy 84.1Unverified
7Gopher-280B (few-shot, k=5)Accuracy 83.9Unverified
8Gopher-280B (few-shot, k=5)Accuracy83.3Unverified
9Gopher-280B (few-shot, k=5)Accuracy 81.8Unverified
10Gopher-280B (few-shot, k=5)Accuracy 81Unverified