Sonya-7B [bfloat16] [rev: 228e7ab8b24e]: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1418 ± 34, rank #5273 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC261.22MC2 (%) (0-shot)77.2
Open LLM Leaderboard v1 - HellaSwag85.11Normalized accuracy (%) (10-shot)71.9
Open LLM Leaderboard v1 - GSM8K59.51Accuracy (%) (5-shot)71.3
Open LLM Leaderboard v1 - ARC Challenge64.59Normalized accuracy (%) (25-shot)67.3
Open LLM Leaderboard v1 - WinoGrande77.74Accuracy (%) (5-shot)58.2
Open LLM Leaderboard v1 - MMLU62.72Accuracy (%) (5-shot)56.5

Interactive version: theaggregate.ai/model?slug=sonya-7b-bfloat16-rev-228e7ab8b24e · How It Works · Data refreshed daily, snapshot 2026-11-08.