zephyr-smol_llama-100m-dpo-full: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1105 ± 39, rank #10666 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC245.75MC2 (%) (0-shot)32
Open LLM Leaderboard v1 - GSM8K0.68Accuracy (%) (5-shot)13.5
Open LLM Leaderboard v1 - MMLU25.18Accuracy (%) (5-shot)6.9
Open LLM Leaderboard v1 - HellaSwag28.54Normalized accuracy (%) (10-shot)4.8
Open LLM Leaderboard v1 - WinoGrande51.07Accuracy (%) (5-shot)4.8
Open LLM Leaderboard v1 - ARC Challenge25Normalized accuracy (%) (25-shot)4.3

Interactive version: theaggregate.ai/model?slug=zephyr-smol-llama-100m-dpo-full · How It Works · Data refreshed daily, snapshot 2026-11-08.