Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Factuality on TruthfulQA

99.5Quality Score

Otrue

Updated 29d ago

Evaluation Results

Method	Links
Otrue 2026.06		99.5	57.1
SOTA LLM 2026.06		98.8	-

SOTA Paper

Otrue

The Capability Frontier: Benchmarks Miss 82% of Model Performance

Dataset

TruthfulQA

Follow for update

@wizwand_team Discord

Related Benchmarks

Question Answering on GPQA Diamond (Quality, Cost, and Error Reduction)Instruction Following on LiveBench IFEval Agentic Code Generation on LiveBench-Coding agentic Code Generation on LiveBench Coding Competitive Programming on LeetCode

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs