Codellama-7B-hf-ReFT-GSM8k: benchmark results

Provider: Meta. Access: Open.

Aggregate Rating 1252 ± 35, rank #9241 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K23.73Accuracy (%) (5-shot)43.1
Open LLM Leaderboard v1 - MMLU40.86Accuracy (%) (5-shot)21.4
Open LLM Leaderboard v1 - ARC Challenge43.52Normalized accuracy (%) (25-shot)19.3
Open LLM Leaderboard v1 - WinoGrande64.25Accuracy (%) (5-shot)17.1
Open LLM Leaderboard v1 - HellaSwag64.53Normalized accuracy (%) (10-shot)16.9
Open LLM Leaderboard v1 - TruthfulQA MC237.28MC2 (%) (0-shot)5.4

Interactive version: theaggregate.ai/model?slug=codellama-7b-hf-reft-gsm8k · How It Works · Data refreshed daily, snapshot 2026-11-08.