deep-solar-v2.0.1: benchmark results

Provider: Other. Access: Open.

Unified ELO 1397 ± 17, rank #1932 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-Winogrande65.04Accuracy (%)82.2
Open Korean LLM - KorNAT-Helpful49.68Normalized accuracy (%)80.7
Open Korean LLM - KorNAT-Harmless64.61Normalized accuracy (%)75.4
Open Korean LLM - Ko-GSM8K (flexible extract)19.11Exact match, flexible extract (%)50.4
Open Korean LLM - Ko-IFEval27.42Strict accuracy, prompt/instruction mean (%)43
Open Korean LLM - KorNAT-CKA22.89Normalized accuracy (%)41.5
Open Korean LLM - Ko-GPQA-Diamond22.73Normalized accuracy (%)40.9
Open Korean LLM Leaderboard32.86Average Score (%)36.1
Open Ko-LLM Leaderboard32.86Average (%)35.9
Open Korean LLM - Ko-EQ-Bench-6.51EQ-Bench score2.2

Interactive version: theaggregate.ai/model?slug=deep-solar-v2-0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.