Kaiju-11B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1459 ± 36, rank #3364 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande83.5Accuracy (%) (5-shot)89.2
Open LLM Leaderboard v1 - MMLU66.79Accuracy (%) (5-shot)88.2
Open LLM Leaderboard v1 - HellaSwag87.72Normalized accuracy (%) (10-shot)87.5
Open LLM Leaderboard v1 - ARC Challenge69.97Normalized accuracy (%) (25-shot)84.7
Open LLM Leaderboard v1 - GSM8K66.79Accuracy (%) (5-shot)82.5
Open LLM Leaderboard v1 - TruthfulQA MC262.15MC2 (%) (0-shot)78.7

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