ContextualAI/LMUnit-llama3.1-70b
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:32kPublished:Jul 19, 2025Architecture:Transformer0.0K Cold

Contextual AI's LMUnit-llama3.1-70b is a 70 billion parameter language model fine-tuned from Llama-3.1-70B-Instruct, specifically optimized for evaluating natural language unit tests. It takes a prompt, a response, and a unit test as input, producing a continuous score indicating how well the response satisfies the test criteria. This model achieves leading performance in fine-grained evaluation tasks and demonstrates high alignment with human preferences, ranking in the top 5 of the RewardBench benchmark with 93.5% accuracy.

Loading preview...