https://hyper.ai/en/sota/tasks/text-generation/benchmark/tvmegasite-dev 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/tvmegasite-test 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/twitter-dialogue-noun 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/twitter-dialogue-tense 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/ubuntu-dialogue-activity 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/ubuntu-dialogue-cmd 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/ubuntu-dialogue-entity 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/ubuntu-dialogue-tense 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/ubuntu-irc 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/unknown 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/user%20study%20dataset 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/uspto-backgrounds 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/vg-graph-text 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/visual-question-generation 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/webnlg-v2-1 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/WebNLG17 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/wikiofgraph 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/WildBench%2C%20Arena-Hard 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/WMT'19%20De-En 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/WMT14%20German-to-English 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/text-generation/benchmark/writingprompts 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/POPE 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/kilt-fever 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MedClaim 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/StrategyClaim 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/TruthfulClaim 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/B-score%20evaluation%20set 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/AMBER 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CorFEVER 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/FEVER 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/BEAF 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CSQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/HLE 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/tabfact 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MuSiQue 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MedMCQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/AVeriTeC 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/fnc-1 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MediEval 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/SQuAD 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/GQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/LIAR 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMRel 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/R-Bench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/TruthfulQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/AVHBench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/COCO 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/HotpotQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MOCHEG 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/PhD 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/SNLI 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/VERITE 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/A-OKVQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/ARC-C 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/HellaSwag 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/NewsCLIPpings 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/PubmedQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/BIG-Bench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CosmosQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/FaithEval 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/FakeHealth 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/LLaVA-Bench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MedQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MISBENCH 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMFakeBench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Anatomy 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Clinic 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Col-Bio 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Col-Med 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Gene 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMLU%20Pro-Med 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MovieSum 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MSCOCO 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/PubHealth 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/RAGTruth 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/rawfc 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/RPE 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/SCIFACT 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/Biography 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CICERO%20V1 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CICERO%20V2 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CLAIMREVIEW2024%2B 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/CommonsenseQA%202.0 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/Disagreement%20Set 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/EG-QA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/FActScore 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/Feverous 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/grover-mega 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/HallusionBench 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/HOVER 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMEval-Pro 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/MMVP 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/PIQA 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/POPE-A 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/POPE-P 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/POPE-R 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/QASC 2026-08-20T07:36:05.854Z https://hyper.ai/en/sota/tasks/factual-consistency/benchmark/RealWorldQA 2026-08-20T07:36:05.854Z