zephyr-7B-sft-full-SPIN-iter0 [float16] [rev: d457f58ca73B]: benchmark results

Provider: HuggingFace. Access: Open.

Aggregate Rating 1399 ± 33, rank #6128 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.43Normalized accuracy (%) (10-shot)66.1
Open LLM Leaderboard v1 - ARC Challenge63.57Normalized accuracy (%) (25-shot)63.3
Open LLM Leaderboard v1 - WinoGrande77.98Accuracy (%) (5-shot)59.9
Open LLM Leaderboard v1 - GSM8K36.32Accuracy (%) (5-shot)51.7
Open LLM Leaderboard v1 - MMLU61.28Accuracy (%) (5-shot)51.3
Open LLM Leaderboard v1 - TruthfulQA MC250.34MC2 (%) (0-shot)48

Interactive version: theaggregate.ai/model?slug=zephyr-7b-sft-full-spin-iter0-float16-rev-d457f58ca73b · How It Works · Data refreshed daily, snapshot 2026-11-08.