jaskier-7B-dpo-v4.3: benchmark results

Provider: Other.

Aggregate Rating 1464 ± 43, rank #2987 of 10870 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC278.27MC2 (%) (0-shot)98.8
Open LLM Leaderboard v1 - HellaSwag89.09Normalized accuracy (%) (10-shot)96.9
Open LLM Leaderboard v1 - WinoGrande84.77Accuracy (%) (5-shot)95
Open LLM Leaderboard v1 - ARC Challenge72.61Normalized accuracy (%) (25-shot)92.8
Open LLM Leaderboard v1 - GSM8K69.07Accuracy (%) (5-shot)87.9
Open LLM Leaderboard v1 - MMLU64.29Accuracy (%) (5-shot)67.8

Interactive version: theaggregate.ai/model?slug=jaskier-7b-dpo-v4-3 · How It Works · Data refreshed daily, snapshot 2026-11-12.