otter3.1.3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1333 ± 17, rank #2329 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 26.71 | Normalized accuracy (%) | 66.3 |
| Open Korean LLM - Ko-Winogrande | 60.22 | Accuracy (%) | 52.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 3.87 | Exact match, flexible extract (%) | 22.1 |
| Open Korean LLM - KorNAT-Helpful | 42.38 | Normalized accuracy (%) | 15.7 |
| Open Korean LLM Leaderboard | 29.65 | Average Score (%) | 12.8 |
| Open Ko-LLM Leaderboard | 29.65 | Average (%) | 12.7 |
| Open Korean LLM - Ko-IFEval | 6.39 | Strict accuracy, prompt/instruction mean (%) | 6.4 |
| Open Korean LLM - KorNAT-Harmless | 57.03 | Normalized accuracy (%) | 1.3 |
Interactive version: theaggregate.ai/model?slug=otter3-1-3 · How It Works · Data refreshed daily, snapshot 2026-09-19.