Reyna-CoT-4B-v0.2: benchmark results

Provider: Other.

Aggregate Rating 1300 ± 42, rank #8734 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K19.71Accuracy (%) (5-shot)40.8
Open LLM Leaderboard v1 - MMLU53.82Accuracy (%) (5-shot)33.2
Open LLM Leaderboard v1 - HellaSwag69Normalized accuracy (%) (10-shot)19.7
Open LLM Leaderboard v1 - WinoGrande65.51Accuracy (%) (5-shot)19
Open LLM Leaderboard v1 - ARC Challenge39.68Normalized accuracy (%) (25-shot)16
Open LLM Leaderboard v1 - TruthfulQA MC239.8MC2 (%) (0-shot)12

Interactive version: theaggregate.ai/model?slug=reyna-cot-4b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.