Tess-v2.5-Gemma-2-27B-alpha: benchmark results
Provider: Other. Access: Open.
Unified ELO 1572 ± 17, rank #746 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 49.08 | Average Score (%) | 96.5 |
| Open Ko-LLM Leaderboard | 49.08 | Average (%) | 96.4 |
| Open Korean LLM - Ko-IFEval | 54.38 | Strict accuracy, prompt/instruction mean (%) | 96.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 61.79 | Exact match, flexible extract (%) | 95.2 |
| Open Korean LLM - Ko-EQ-Bench | 48.19 | EQ-Bench score | 94.7 |
| Open Korean LLM - KorNAT-CKA | 33.44 | Normalized accuracy (%) | 91.9 |
| Open Korean LLM - KorNAT-Harmless | 66.07 | Normalized accuracy (%) | 84 |
| Open Korean LLM - KorNAT-Helpful | 49.85 | Normalized accuracy (%) | 82.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - Ko-Winogrande | 64.88 | Accuracy (%) | 81.2 |
Interactive version: theaggregate.ai/model?slug=tess-v2-5-gemma-2-27b-alpha · How It Works · Data refreshed daily, snapshot 2026-09-19.