SemanticAlign-Bench - Method and Formula: leaderboard

Metric: Semantic alignment score (0-1; method and formula claims (algorithm steps, equations, component interfaces); 30 ICLR, ICML and NeurIPS 2025 papers with 1,491 atomic implementation claims; the agent reads the paper and writes a reproduction repository, and GPT-5.5 scores each claim against the code on a five-level rubric (0, 0.25, 0.5, 0.75, 1) without executing it; mean over the 30 paper-level scores). Source: arxiv.org. Saturation forecast: Around October 2027. 12 models tracked.

Top models

#ModelScore
1DeepSeek V4 Pro0.3
2Claude Sonnet 4.60.27
3Gemini 2.5 Flash0.26
4GPT-4o0.1

Interactive version: theaggregate.ai/benchmark?slug=semanticalign-bench-method-and-formula · How It Works · Data refreshed daily, snapshot 2026-09-29.