TinyLlama-Remix: benchmark results

Provider: Singapore Univ. Access: Open.

Aggregate Rating 1136 ± 36, rank #10206 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU27.34Accuracy (%) (5-shot)15.1
Open LLM Leaderboard v1 - TruthfulQA MC240.53MC2 (%) (0-shot)14.5
Open LLM Leaderboard v1 - HellaSwag49.5Normalized accuracy (%) (10-shot)10.2
Open LLM Leaderboard v1 - ARC Challenge31.14Normalized accuracy (%) (25-shot)10
Open LLM Leaderboard v1 - GSM8K0.08Accuracy (%) (5-shot)9.5
Open LLM Leaderboard v1 - WinoGrande55.41Accuracy (%) (5-shot)9.1

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