suzume-llama-3-8B-multilingual-orpo-borda-half: benchmark results
Provider: Lightblue. Released 2024-04-25. Access: Open.
Unified ELO 1461 ± 1, rank #894 of 1392 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 45.06 | Average Score (%) | 91 |
| Open LLM Leaderboard - IFEval | 62.49 | Score | 74.5 |
| Open Chinese LLM - GSM8K | 49.05 | Accuracy (%) | 63.9 |
| Ru Arena Hard | 57.13 | Win Rate (%) | 56.3 |
| Open Chinese LLM - WinoGrande | 63.38 | Accuracy (%) | 55.8 |
| Open LLM Leaderboard - MMLU-Pro | 29.04 | Score | 55.4 |
| Open Chinese LLM - CMMLU | 53.6 | Accuracy (%) | 51.6 |
| Open Chinese LLM - HellaSwag | 59.81 | Accuracy (%) | 48.1 |
| Open Chinese LLM - C-Eval Semantic | 68.59 | Accuracy (%) | 46.4 |
| Open LLM Leaderboard - MATH Level 5 | 9.06 | Score | 44.4 |
| Open Chinese LLM Leaderboard | 56.01 | Average Score (%) | 43.6 |
| Open LLM Leaderboard - BBH | 26.35 | Score | 41.1 |
Interactive version: theaggregate.ai/model?slug=suzume-llama-3-8b-multilingual-orpo-borda-half · How It Works · Data refreshed daily, snapshot 2026-09-05.