The Eval Index / Reasoning / #162
ai-twinkle/Eval
by ai-twinkle · Reasoning · updated 1mo ago
High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.
48
momentum
117
stars
17
forks
#162
rank
evalevaluationllm
View on GitHub →