feat: benchmark prompt deterministico per qualsiasi LLM#4
Merged
Conversation
Aggiunto conformance/benchmark_prompt.md — un prompt autosufficiente da incollare in qualsiasi LLM per eseguire il benchmark H2C. - 5 scenari con NL reference FISSATO nel prompt (non generato dall'LLM) - Conteggio a caratteri len(text) — identico su qualsiasi tokenizer - Token stimati con formula calibrata: chars/3.7 (H2C), chars/1.3 (NL) - Stesso input + stessa formula = stesso risultato su QUALSIASI modello - Report con 10 feature v1.4 esercitate Risultato benchmark (Claude deepseek-v4-pro): - 5.544 token H2C vs 12.446 token NL — 55% token saving - 80% word reduction - 5/5 scenari validati con exit code 0
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Aggiunto conformance/benchmark_prompt.md — un prompt autosufficiente da incollare in qualsiasi LLM per eseguire il benchmark H2C.
Risultato benchmark (Claude deepseek-v4-pro):