Research domain
LLM (Chat & Instruction)
Mathematical Reasoning3,780 benchmarks · 2,524 papersReasoning677 benchmarks · 627 papersInstruction Following462 benchmarks · 591 papersHallucination Detection420 benchmarks · 178 papersMath Reasoning316 benchmarks · 238 papersReward Modeling228 benchmarks · 114 papersGenerative Modeling227 benchmarks · 111 papersGeneral Reasoning163 benchmarks · 199 papersKnowledge Editing139 benchmarks · 53 papersLong-context Understanding131 benchmarks · 153 papersHallucination Evaluation129 benchmarks · 196 papersMulti-task Language Understanding123 benchmarks · 294 papersLLM-generated text detection120 benchmarks · 15 papersFunction Calling115 benchmarks · 88 papersJailbreaking107 benchmarks · 65 papersLong-context Question Answering104 benchmarks · 77 papersMath103 benchmarks · 94 papersDialogue Generation85 benchmarks · 64 papersSpeculative Decoding80 benchmarks · 39 papersLong-context Language Understanding79 benchmarks · 117 papersLong-context retrieval79 benchmarks · 54 papersMultitask Language Understanding77 benchmarks · 172 papersArithmetic Reasoning76 benchmarks · 106 papersTool Calling75 benchmarks · 37 papersLong-context Reasoning70 benchmarks · 65 papersLLM Routing65 benchmarks · 19 papersZero-shot Evaluation63 benchmarks · 80 papersPreference Alignment61 benchmarks · 32 papersOpen-ended generation56 benchmarks · 44 papersGeneration56 benchmarks · 32 papersMulti-hop Reasoning54 benchmarks · 44 papersModel Editing53 benchmarks · 20 papers