Infinity-Instruct-3M-0625-Llama3-8B: benchmark results
BAAI's Llama 3 8B tuned on the Infinity-Instruct 3M foundational set plus the 0625 chat stage, SFT-only with no RLHF. Provider: BAAI. Released 2024-07-09. Access: Open.
Aggregate Rating 1474 ± 15, rank #870 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 49.87 | Strict accuracy, prompt/instruction mean (%) | 93.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 59.21 | Exact match, flexible extract (%) | 93.2 |
| Open Korean LLM Leaderboard | 46.35 | Average Score (%) | 93 |
| Open Ko-LLM Leaderboard | 46.35 | Average (%) | 92.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - Ko-EQ-Bench | 36.69 | EQ-Bench score | 87.1 |
| Open Korean LLM - KorNAT-Helpful | 50.3 | Normalized accuracy (%) | 85.1 |
| Open Chinese LLM - GSM8K | 57.62 | Accuracy (%) | 80 |
| Open Portuguese LLM - ENEM | 69.7 | Accuracy (%) | 73.8 |
| Open Korean LLM - KorNAT-Harmless | 64.36 | Normalized accuracy (%) | 73.3 |
| Open LLM Leaderboard - IFEval | 60.5 | Score | 72.4 |
| Open Portuguese LLM - OAB Exams | 49.11 | Accuracy (%) | 71.5 |
Interactive version: theaggregate.ai/model?slug=infinity-instruct-3m-0625-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-10-20.