Excalibur-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1455 ± 37, rank #3527 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag87.56Normalized accuracy (%) (10-shot)86.8
Open LLM Leaderboard v1 - GSM8K68.61Accuracy (%) (5-shot)86.4
Open LLM Leaderboard v1 - TruthfulQA MC267.24MC2 (%) (0-shot)85.7
Open LLM Leaderboard v1 - WinoGrande82.79Accuracy (%) (5-shot)85.6
Open LLM Leaderboard v1 - MMLU65.66Accuracy (%) (5-shot)85.1
Open LLM Leaderboard v1 - ARC Challenge69.71Normalized accuracy (%) (25-shot)84

Interactive version: theaggregate.ai/model?slug=excalibur-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.