SOVLish-Devil-8B-L3: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1454 ± 34, rank #3603 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K72.48Accuracy (%) (5-shot)97.9
Open LLM Leaderboard v1 - MMLU68.97Accuracy (%) (5-shot)92.1
Open LLM Leaderboard v1 - ARC Challenge69.2Normalized accuracy (%) (25-shot)82.5
Open LLM Leaderboard v1 - TruthfulQA MC257.95MC2 (%) (0-shot)71.4
Open LLM Leaderboard v1 - HellaSwag84.44Normalized accuracy (%) (10-shot)66.2
Open LLM Leaderboard v1 - WinoGrande78.14Accuracy (%) (5-shot)60.9

Interactive version: theaggregate.ai/model?slug=sovlish-devil-8b-l3 · How It Works · Data refreshed daily, snapshot 2026-11-08.