Grafted-Llama2-2x70B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1487 ± 35, rank #2561 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag89.57Normalized accuracy (%) (10-shot)99.4
Open LLM Leaderboard v1 - MMLU71.67Accuracy (%) (5-shot)95.2
Open LLM Leaderboard v1 - WinoGrande84.37Accuracy (%) (5-shot)93.1
Open LLM Leaderboard v1 - ARC Challenge72.61Normalized accuracy (%) (25-shot)92.8
Open LLM Leaderboard v1 - TruthfulQA MC266.49MC2 (%) (0-shot)84.9
Open LLM Leaderboard v1 - GSM8K57.92Accuracy (%) (5-shot)69.6

Interactive version: theaggregate.ai/model?slug=grafted-llama2-2x70b · How It Works · Data refreshed daily, snapshot 2026-11-08.