jaskier-7B-dpo-v4.1: benchmark results

Provider: Other.

Aggregate Rating 1467 ± 43, rank #2956 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag89.07Normalized accuracy (%) (10-shot)96.6
Open LLM Leaderboard v1 - TruthfulQA MC275.92MC2 (%) (0-shot)95.8
Open LLM Leaderboard v1 - ARC Challenge72.95Normalized accuracy (%) (25-shot)94.5
Open LLM Leaderboard v1 - WinoGrande84.69Accuracy (%) (5-shot)94.4
Open LLM Leaderboard v1 - GSM8K68.31Accuracy (%) (5-shot)85.7
Open LLM Leaderboard v1 - MMLU64.75Accuracy (%) (5-shot)75.9

Interactive version: theaggregate.ai/model?slug=jaskier-7b-dpo-v4-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.