TinyWand-DPO: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1140 ± 34, rank #10112 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC245.8MC2 (%) (0-shot)32.3
Open LLM Leaderboard v1 - GSM8K1.9Accuracy (%) (5-shot)18.7
Open LLM Leaderboard v1 - MMLU26.22Accuracy (%) (5-shot)11.7
Open LLM Leaderboard v1 - ARC Challenge31.66Normalized accuracy (%) (25-shot)10.4
Open LLM Leaderboard v1 - HellaSwag50.42Normalized accuracy (%) (10-shot)10.4
Open LLM Leaderboard v1 - WinoGrande54.78Accuracy (%) (5-shot)8.6

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