test3_sft_16bit: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1468 ± 43, rank #2778 of 10870 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - ARC Challenge73.55Normalized accuracy (%) (25-shot)97.7
Open LLM Leaderboard v1 - HellaSwag88.87Normalized accuracy (%) (10-shot)94.6
Open LLM Leaderboard v1 - WinoGrande84.45Accuracy (%) (5-shot)93.4
Open LLM Leaderboard v1 - GSM8K70.43Accuracy (%) (5-shot)93
Open LLM Leaderboard v1 - TruthfulQA MC269.77MC2 (%) (0-shot)89.4
Open LLM Leaderboard v1 - MMLU64.63Accuracy (%) (5-shot)73.9

Interactive version: theaggregate.ai/model?slug=test3-sft-16bit · How It Works · Data refreshed daily, snapshot 2026-11-12.