LLaMA-Pro-8B: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1372 ± 19, rank #2332 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR40.18Score43.3
Open LLM Leaderboard v1 - GSM8K17.82Accuracy (%) (5-shot)39.3
Open LLM Leaderboard v1 - WinoGrande74.19Accuracy (%) (5-shot)35.4
Open LLM Leaderboard v1 - HellaSwag77.91Normalized accuracy (%) (10-shot)32.3
Open LLM Leaderboard v1 - ARC Challenge53.75Normalized accuracy (%) (25-shot)30.2
Open LLM Leaderboard v1 - MMLU47.49Accuracy (%) (5-shot)26.4
Open LLM Leaderboard - MMLU-Pro18.11Score19.8
Open LLM Leaderboard - BBH34.84Score18.7
Open LLM Leaderboard - IFEval22.77Score16
Open LLM Leaderboard - MATH Level 51.89Score13.3
Open LLM Leaderboard - GPQA26.01Score13.2
Open LLM Leaderboard v1 - TruthfulQA MC238.86MC2 (%) (0-shot)9.3

Interactive version: theaggregate.ai/model?slug=llama-pro-8b · How It Works · Data refreshed daily, snapshot 2026-09-23.