Cucumber-7B-10k: benchmark results

Provider: Other.

Aggregate Rating 1403 ± 32, rank #5955 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande78.93Accuracy (%) (5-shot)66.3
Open LLM Leaderboard v1 - HellaSwag83.75Normalized accuracy (%) (10-shot)61.2
Open LLM Leaderboard v1 - MMLU63.1Accuracy (%) (5-shot)58.3
Open LLM Leaderboard v1 - GSM8K39.27Accuracy (%) (5-shot)54.2
Open LLM Leaderboard v1 - TruthfulQA MC250.97MC2 (%) (0-shot)50.1
Open LLM Leaderboard v1 - ARC Challenge60.41Normalized accuracy (%) (25-shot)47.5

Interactive version: theaggregate.ai/model?slug=cucumber-7b-10k · How It Works · Data refreshed daily, snapshot 2026-11-08.