flair/mastermind_24_mcq_random
Viewer • Updated • 30.4k • 367
MastermindEval
Prompting and multiple-choice (MCQ) benchmarks to evaluate reasoning capabilities of LLMs using Mastermind.
-
-
flair/mastermind_35_mcq_random
Viewer • Updated • 37.1k • 69 -
flair/mastermind_46_mcq_random
Viewer • Updated • 36.1k • 348 -
flair/mastermind_24_mcq_close
Viewer • Updated • 30.4k • 82 -
flair/mastermind_35_mcq_close
Viewer • Updated • 37.1k • 106 -
flair/mastermind_46_mcq_close
Viewer • Updated • 36.1k • 142 -
flair/mastermind_24_prompt
Viewer • Updated • 30.4k • 42 -
flair/mastermind_35_prompt
Viewer • Updated • 37.1k • 30 -
flair/mastermind_46_prompt
Viewer • Updated • 36.1k • 27 -
MastermindEval: A Simple But Scalable Reasoning Benchmark
Paper • 2503.05891 • Published • 1 -
flair/mastermind_57_mcq_random
Viewer • Updated • 1.23k • 48 -
flair/mastermind_57_mcq_close
Viewer • Updated • 1.23k • 46 -
flair/mastermind_68_mcq_random
Viewer • Updated • 1.27k • 46 -
flair/mastermind_68_mcq_close
Viewer • Updated • 1.27k • 48