finetuned-llama2-2048-v3.0 [4bit]: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1300 ± 33, rank #8741 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K14.94Accuracy (%) (5-shot)36.9
Open LLM Leaderboard v1 - TruthfulQA MC246.21MC2 (%) (0-shot)33.8
Open LLM Leaderboard v1 - HellaSwag77.09Normalized accuracy (%) (10-shot)30.2
Open LLM Leaderboard v1 - WinoGrande72.06Accuracy (%) (5-shot)28.1
Open LLM Leaderboard v1 - MMLU46.69Accuracy (%) (5-shot)25.3
Open LLM Leaderboard v1 - ARC Challenge49.83Normalized accuracy (%) (25-shot)24.3

Interactive version: theaggregate.ai/model?slug=finetuned-llama2-2048-v3-0-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.