fietje-2B-chat [float16] [rev: 08b3ae1f44ea]: benchmark results

Provider: Other.

Aggregate Rating 1307 ± 34, rank #8601 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - ARC Challenge53.84Normalized accuracy (%) (25-shot)30.3
Open LLM Leaderboard v1 - MMLU50.33Accuracy (%) (5-shot)29.7
Open LLM Leaderboard v1 - WinoGrande71.35Accuracy (%) (5-shot)26.4
Open LLM Leaderboard v1 - GSM8K5.61Accuracy (%) (5-shot)24.5
Open LLM Leaderboard v1 - HellaSwag68.95Normalized accuracy (%) (10-shot)19.7
Open LLM Leaderboard v1 - TruthfulQA MC241.95MC2 (%) (0-shot)18.8

Interactive version: theaggregate.ai/model?slug=fietje-2b-chat-float16-rev-08b3ae1f44ea · How It Works · Data refreshed daily, snapshot 2026-11-08.