Defne-llama3.1-8B — benchmark results
Eurdem's Turkish-English fine-tune of Llama 3.1 8B Instruct, trained on ~4M Turkish tokens and merged with SauerkrautLM. Provider: Other. Released 2024-07-29. Access: Open.
Unified ELO 1457 ± 14, rank #966 of 1776 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 485.81 | Average Score (%) | 86 |
| Open LLM Leaderboard - MuSR | 13.54 | Score | 74.5 |
| Open LLM Leaderboard - MMLU-Pro | 31.84 | Score | 69 |
| Open LLM Leaderboard - MATH Level 5 | 16.01 | Score | 63.8 |
| Open LLM Leaderboard - BBH | 32.82 | Score | 63.2 |
| Open LLM Leaderboard - IFEval | 50.36 | Score | 59.6 |
| Open LLM Leaderboard - GPQA | 6.15 | Score | 51.6 |
Interactive version: theaggregate.ai/model?slug=defne-llama3-1-8b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.