Llama 2 13B FINETUNE4.3.8w R16 Gate Up Down Test1: benchmark results

Provider: Meta. Access: Open.

Aggregate Rating 1351 ± 34, rank #7672 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande77.43Accuracy (%) (5-shot)55.8
Open LLM Leaderboard v1 - HellaSwag82.27Normalized accuracy (%) (10-shot)49.9
Open LLM Leaderboard v1 - MMLU55.63Accuracy (%) (5-shot)36.9
Open LLM Leaderboard v1 - GSM8K12.66Accuracy (%) (5-shot)34.5
Open LLM Leaderboard v1 - ARC Challenge55.8Normalized accuracy (%) (25-shot)34.2
Open LLM Leaderboard v1 - TruthfulQA MC238.15MC2 (%) (0-shot)7.5

Interactive version: theaggregate.ai/model?slug=llama-2-13b-finetune4-3-8w-r16-gate-up-down-test1 · How It Works · Data refreshed daily, snapshot 2026-11-08.