GEITje-7B-chat-v2: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1306 ± 32, rank #8614 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K16.22Accuracy (%) (5-shot)38
Open LLM Leaderboard v1 - MMLU49Accuracy (%) (5-shot)28.2
Open LLM Leaderboard v1 - WinoGrande71.51Accuracy (%) (5-shot)26.7
Open LLM Leaderboard v1 - ARC Challenge50.34Normalized accuracy (%) (25-shot)24.7
Open LLM Leaderboard v1 - HellaSwag74.13Normalized accuracy (%) (10-shot)24.4
Open LLM Leaderboard v1 - TruthfulQA MC243.55MC2 (%) (0-shot)24

Interactive version: theaggregate.ai/model?slug=geitje-7b-chat-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.