spicyboros-70B-2.2: benchmark results

Provider: Jon Durbin. Access: Open.

Aggregate Rating 1467 ± 34, rank #2940 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU70.32Accuracy (%) (5-shot)93.7
Open LLM Leaderboard v1 - WinoGrande83.82Accuracy (%) (5-shot)90.8
Open LLM Leaderboard v1 - HellaSwag87.58Normalized accuracy (%) (10-shot)86.9
Open LLM Leaderboard v1 - ARC Challenge70.73Normalized accuracy (%) (25-shot)86.8
Open LLM Leaderboard v1 - TruthfulQA MC258.31MC2 (%) (0-shot)72
Open LLM Leaderboard v1 - GSM8K40.94Accuracy (%) (5-shot)56.1

Interactive version: theaggregate.ai/model?slug=spicyboros-70b-2-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.