SpellBlade: benchmark results

Provider: Other.

Aggregate Rating 1463 ± 33, rank #3152 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU70.5Accuracy (%) (5-shot)94
Open LLM Leaderboard v1 - WinoGrande83.19Accuracy (%) (5-shot)87.5
Open LLM Leaderboard v1 - HellaSwag87.31Normalized accuracy (%) (10-shot)85.4
Open LLM Leaderboard v1 - ARC Challenge69.28Normalized accuracy (%) (25-shot)82.7
Open LLM Leaderboard v1 - GSM8K53.83Accuracy (%) (5-shot)65.6
Open LLM Leaderboard v1 - TruthfulQA MC247.1MC2 (%) (0-shot)36.5

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