Infinity-Instruct-7M-0729-Llama3.1-8B: benchmark results
BAAI's Llama 3.1 8B Infinity-Instruct SFT tune under its original 0729 dataset name - the same checkpoint later renamed 7M-Gen. Provider: BAAI. Released 2024-08-02. Access: Open.
Aggregate Rating 1471 ± 17, rank #886 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 60.05 | Exact match, flexible extract (%) | 93.9 |
| Open Korean LLM - Ko-IFEval | 50.32 | Strict accuracy, prompt/instruction mean (%) | 93.8 |
| Open Korean LLM Leaderboard | 45.96 | Average Score (%) | 92.5 |
| Open Ko-LLM Leaderboard | 45.96 | Average (%) | 92.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - Ko-EQ-Bench | 39.19 | EQ-Bench score | 90.1 |
| Open Portuguese LLM - ASSIN2 RTE | 93.54 | Macro F1 (%) | 90 |
| Open Korean LLM - KorNAT-Helpful | 49.23 | Normalized accuracy (%) | 77.8 |
| Open Portuguese LLM - ENEM | 70.82 | Accuracy (%) | 77.8 |
| Open Chinese LLM - GSM8K | 55.34 | Accuracy (%) | 76.2 |
| Open Portuguese LLM - BLUEX | 58.83 | Accuracy (%) | 74.9 |
| Open LLM Leaderboard - IFEval | 61.32 | Score | 73.4 |
Interactive version: theaggregate.ai/model?slug=infinity-instruct-7m-0729-llama3-1-8b · How It Works · Data refreshed daily, snapshot 2026-10-20.