komt_mistral_mss_user_0_max_steps_80: benchmark results
Provider: Other. Access: Open.
Unified ELO 1366 ± 17, rank #2133 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 30.32 | Strict accuracy, prompt/instruction mean (%) | 55.5 |
| Open Korean LLM - KorNAT-CKA | 21.65 | Normalized accuracy (%) | 35.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.54 | Exact match, flexible extract (%) | 34.4 |
| Open Korean LLM - KorNAT-Helpful | 44.52 | Normalized accuracy (%) | 30.2 |
| Open Korean LLM Leaderboard | 31.18 | Average Score (%) | 26.1 |
| Open Ko-LLM Leaderboard | 31.18 | Average (%) | 25.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
| Open Korean LLM - KorNAT-Harmless | 60.58 | Normalized accuracy (%) | 16.1 |
| Open Korean LLM - Ko-Winogrande | 53.91 | Accuracy (%) | 14.6 |
| Open Korean LLM - Ko-EQ-Bench | -1.76 | EQ-Bench score | 3.5 |
Interactive version: theaggregate.ai/model?slug=komt-mistral-mss-user-0-max-steps-80 · How It Works · Data refreshed daily, snapshot 2026-09-19.