Llama 2 13B FINETUNE4.3.8w R8 Gate Up Down: benchmark results

Provider: Meta. Access: Open.

Aggregate Rating 1347 ± 34, rank #7782 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande77.19Accuracy (%) (5-shot)53.9
Open LLM Leaderboard v1 - HellaSwag82.13Normalized accuracy (%) (10-shot)49
Open LLM Leaderboard v1 - MMLU55.33Accuracy (%) (5-shot)36
Open LLM Leaderboard v1 - GSM8K12.89Accuracy (%) (5-shot)34.8
Open LLM Leaderboard v1 - ARC Challenge54.35Normalized accuracy (%) (25-shot)31.2
Open LLM Leaderboard v1 - TruthfulQA MC239.6MC2 (%) (0-shot)11.5

Interactive version: theaggregate.ai/model?slug=llama-2-13b-finetune4-3-8w-r8-gate-up-down · How It Works · Data refreshed daily, snapshot 2026-11-08.