Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge: benchmark results
Provider: Meta. Released 2024-06-28. Access: Open.
Unified ELO 1505 ± 1, rank #668 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 68.06 | Score | 80.7 |
| Open Korean LLM Leaderboard | 40.21 | Average Score (%) | 73.3 |
| Open Chinese LLM - TruthfulQA MC | 56.24 | Accuracy (%) | 67.4 |
| Open Chinese LLM - GSM8K | 49.81 | Accuracy (%) | 66.5 |
| Open LLM Leaderboard - MMLU-Pro | 29.83 | Score | 59.1 |
| Open Chinese LLM - C-Eval Semantic | 69.64 | Accuracy (%) | 50.7 |
| Open Chinese LLM Leaderboard | 56.64 | Average Score (%) | 50.4 |
| Open LLM Leaderboard - BBH | 29.07 | Score | 48.6 |
| Open Chinese LLM - CMMLU | 52.97 | Accuracy (%) | 45.7 |
| Open LLM Leaderboard - MATH Level 5 | 8.91 | Score | 43.9 |
| Open Chinese LLM - ARC Challenge | 50.6 | Accuracy (%) | 43 |
| Open LLM Leaderboard - MuSR | 6.7 | Score | 31.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-instruct-8b-simpo-sppo-iter3-merge · How It Works · Data refreshed daily, snapshot 2026-09-05.