oswald-4x7B: benchmark results

Provider: Other.

Aggregate Rating 1430 ± 33, rank #4682 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K66.19Accuracy (%) (5-shot)81.3
Open LLM Leaderboard v1 - HellaSwag85.29Normalized accuracy (%) (10-shot)73.4
Open LLM Leaderboard v1 - MMLU64.49Accuracy (%) (5-shot)71.3
Open LLM Leaderboard v1 - ARC Challenge65.78Normalized accuracy (%) (25-shot)71
Open LLM Leaderboard v1 - TruthfulQA MC257.39MC2 (%) (0-shot)69.9
Open LLM Leaderboard v1 - WinoGrande79.16Accuracy (%) (5-shot)67.7

Interactive version: theaggregate.ai/model?slug=oswald-4x7b · How It Works · Data refreshed daily, snapshot 2026-11-08.