MXLewd-L2-20B: benchmark results

Provider: Undi95. Access: Open.

Aggregate Rating 1375 ± 36, rank #7024 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag85.33Normalized accuracy (%) (10-shot)73.6
Open LLM Leaderboard v1 - ARC Challenge63.23Normalized accuracy (%) (25-shot)61.9
Open LLM Leaderboard v1 - TruthfulQA MC251.65MC2 (%) (0-shot)52.7
Open LLM Leaderboard v1 - WinoGrande76.09Accuracy (%) (5-shot)45.9
Open LLM Leaderboard v1 - MMLU57.36Accuracy (%) (5-shot)41
Open LLM Leaderboard v1 - GSM8K10.92Accuracy (%) (5-shot)32.1

Interactive version: theaggregate.ai/model?slug=mxlewd-l2-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.