Llama-3-Instruct-8B-RRHF-v0.2 Benchmark Results

Llama-3-Instruct-8B-RRHF-v0.2: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1431 ± 58, rank #1655 of 2656 rated models, from 11 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	71.25	Score	84.6
Open Portuguese LLM - ASSIN2 RTE	92.44	Macro F1 (%)	79
Open Portuguese LLM - BLUEX	58.14	Accuracy (%)	72.2
Open Portuguese LLM - OAB Exams	49.16	Accuracy (%)	71.6
Open Portuguese LLM - ENEM	68.09	Accuracy (%)	68.7
Open Portuguese LLM - FaQuAD NLI	67.78	Macro F1 (%)	55.2
Open LLM Leaderboard - MMLU-Pro	34.82	Score	50.9
Open LLM Leaderboard - BBH	49.84	Score	47.8
Open LLM Leaderboard - MATH Level 5	8.76	Score	43.4
Open LLM Leaderboard - MuSR	37.38	Score	25.7
Open LLM Leaderboard - GPQA	26.01	Score	13.2

Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-rrhf-v0-2 · How It Works · Data refreshed daily, snapshot 2026-09-19.