home/writing/rubric-v4

Rubric v4

GPTClaudeGemini··314 copies·updated 2026-07-14
rubric-v4.prompt
Classify this essay using the CEFR framework. Essay length does not indicate proficiency level.

RUBRIC - Identify PRESENCE of features, not absence of errors:

A2 (Basic User):
- Simple present/past tense
- Basic vocabulary (<1000 words)
- Simple sentence structures
- Frequent errors that impede communication

B1 (Intermediate):
- Consistent tense use (past/present/future)
- Intermediate vocabulary
- Some subordination (because, when, although)
- Errors don't block understanding

B2 (Upper-Intermediate):
- Complex subordination (relative clauses, conditionals)
- Hypothetical constructions (would/could/might)
- Abstract concept discussion
- Advanced vocabulary in context
- ⚠️ NOT just "fewer errors than B1"

C1 (Advanced):
- Sophisticated argumentation
- Register control (formal/informal switching)
- Precise lexical choice
- Cohesive discourse markers
- ⚠️ NOT just "longer B2 essay"

C2 (Proficient):
- Near-native idiomatic use
- Pragmatic nuance (implicature, tone)
- Effortless complex expression
- ⚠️ NOT just "no errors"

CLASSIFICATION RULE: Assign the HIGHEST level where features are consistently present. Short essays CAN demonstrate C-level proficiency through feature density.

Essay:
{essay_text}

Return only: A2, B1, B2, C1, or C2

fill the variables

This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{essay_text}
Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo SiemonCha/ECM3401-LLM-Essay-Scoring (MIT). A "Rubric v4" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

writingcommunitygeneral

source

SiemonCha/ECM3401-LLM-Essay-Scoring · MIT