HCAI-Lab/olmes-eval-olmo3-7b-base
Updated • 27
OLMES benchmark evaluation results across OLMo-3-7B and SmolLM-3-3B model variants.
Note OLMo-3-7B base.
Note OLMo-3-7B instruct-base.
Note OLMo-3-7B instruct + chain-of-thought.
Note OLMo-3-7B thinking.
Note SmolLM3-3B base.