deep-solar-Rev-v3.0.4: benchmark results
Provider: Other. Access: Open.
Unified ELO 1402 ± 17, rank #1895 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 67.72 | Accuracy (%) | 91.7 |
| Open Korean LLM - KorNAT-Helpful | 49.08 | Normalized accuracy (%) | 76.2 |
| Open Korean LLM - KorNAT-Harmless | 64.27 | Normalized accuracy (%) | 72.1 |
| Open Korean LLM - Ko-IFEval | 30.35 | Strict accuracy, prompt/instruction mean (%) | 55.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 21 | Exact match, flexible extract (%) | 53.2 |
| Open Korean LLM - Ko-EQ-Bench | 5.58 | EQ-Bench score | 51.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - KorNAT-CKA | 22.62 | Normalized accuracy (%) | 40.5 |
| Open Korean LLM Leaderboard | 32.99 | Average Score (%) | 37.1 |
| Open Ko-LLM Leaderboard | 32.99 | Average (%) | 36.9 |
Interactive version: theaggregate.ai/model?slug=deep-solar-rev-v3-0-4 · How It Works · Data refreshed daily, snapshot 2026-09-19.