deep-solar-v3.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1319 ± 19, rank #2395 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 62.67 | Accuracy (%) | 69.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 20.7 | Exact match, flexible extract (%) | 52.9 |
| Open Korean LLM - KorNAT-CKA | 24.57 | Normalized accuracy (%) | 52 |
| Open Korean LLM - KorNAT-Harmless | 62.69 | Normalized accuracy (%) | 49 |
| Open Korean LLM - KorNAT-Helpful | 44.95 | Normalized accuracy (%) | 33.4 |
| Open Korean LLM - Ko-IFEval | 24.6 | Strict accuracy, prompt/instruction mean (%) | 30.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Ko-LLM Leaderboard | 28.44 | Average (%) | 6.4 |
| Open Korean LLM Leaderboard | 28.44 | Average Score (%) | 6.4 |
| Open Korean LLM - Ko-EQ-Bench | -25.87 | EQ-Bench score | 0.8 |
Interactive version: theaggregate.ai/model?slug=deep-solar-v3-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.