SOTAVerified

General Knowledge

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

Source: BIG-bench

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 399 papers

TitleStatusHype
DIAGen: Diverse Image Augmentation with Generative ModelsCode1
Biomedical Large Languages Models Seem not to be Superior to Generalist Models on Unseen Medical Data—0
CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendation—0
Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small ModelsCode0
RAGEval: Scenario Specific RAG Evaluation Dataset Generation FrameworkCode3
PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning—0
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?Code1
Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian—0
Can Editing LLMs Inject Harm?Code1
Constructing Enhanced Mutual Information for Online Class-Incremental Learning—0
Show:102550
← PrevPage 13 of 40Next →

Benchmark Results

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