Gemma-2-Ataraxy-Gemmasutra-9B-slerp: benchmark results

Community SLERP merge of Gemma 2 9B fine-tunes (Ataraxy and Gemmasutra). Provider: Other. Released 2024-09-11. Access: Open.

Aggregate Rating 1561 ± 21, rank #578 of 1654 rated models, from 20 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-EQ-Bench62.53EQ-Bench score100
Open Korean LLM Leaderboard53.14Average Score (%)98.9
Open Korean LLM - Ko-IFEval65.72Strict accuracy, prompt/instruction mean (%)98.3
Open Korean LLM - Ko-GSM8K (flexible extract)69.14Exact match, flexible extract (%)97.8
Open LLM Leaderboard - IFEval76.49Score92.1
Open Korean LLM - KorNAT-CKA33.02Normalized accuracy (%)90.3
Open Portuguese LLM - ENEM75.65Accuracy (%)89.5
Open LLM Leaderboard - MuSR46.07Score88
Open Portuguese LLM - ASSIN2 RTE93.21Macro F1 (%)87.3
Open Korean LLM - KorNAT-Helpful50.35Normalized accuracy (%)85.4
Open Portuguese LLM - BLUEX64.26Accuracy (%)84.7
Open Portuguese LLM - OAB Exams53.76Accuracy (%)84.3

Interactive version: theaggregate.ai/model?slug=gemma-2-ataraxy-gemmasutra-9b-slerp · How It Works · Data refreshed daily, snapshot 2026-10-24.