RedPajama-INCITE-7B-Instruct: benchmark results

Provider: Together. Released 2023-05-05. Access: Open.

Unified ELO 1295 ± 10, rank #2711 of 2928 rated models, from 107 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HELM Classic - LSAT24.35Exact Match (%)95.6
HELM Classic - CivilComments66.45Exact Match (%)93.9
LLM Trustworthy - Fairness100Trust Score (%)93.8
HELM Classic - bAbI54.53Exact Match (%)79.7
HELM Classic - RAFT69.55Exact Match (%)78.8
HELM Classic - NaturalQuestions Open Book65.92F1 (%)73.8
HELM Classic - LegalSupport56.85Exact Match (%)70.6
MMLU-by-task - College Physics28.43Accuracy (%)67.3
HELM Classic - Entity Matching84.32Exact Match (%)66.7
HELM Classic - TruthfulQA24.31Exact Match (%)56.8
HELM Classic - Entity Data Imputation77.19Exact Match (%)56.1
HELM Classic - MMLU36.31Exact Match (%)53

Interactive version: theaggregate.ai/model?slug=redpajama-incite-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-23.