Olmo 3

Benchmark Model Rank Results
logic-puzzle-solving-on-zebralogicOlmo 3.1 Think 32B#8Accuracy: 80.1
instruction-following-on-ifbenchOlmo 3.1 Think 32B#21Accuracy: 68.1
mathematical-reasoning-on-aime24Olmo 3.1 Think 32B#28Acc: 80.6
mathematical-reasoning-on-aime-2025Olmo 3.1 Think 32B#44Accuracy: 78.1