tinyllama-coder-py-4bit-v10: benchmark results
Provider: Singapore Univ. Access: Open.
Unified ELO 1216 ± 20, rank #2875 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 45.37 | Macro F1 (%) | 27.8 |
| Open Portuguese LLM - ASSIN2 RTE | 41.06 | Macro F1 (%) | 12.9 |
| Open LLM Leaderboard v1 - GSM8K | 0.53 | Accuracy (%) (5-shot) | 12.8 |
| Open LLM Leaderboard v1 - HellaSwag | 56.34 | Normalized accuracy (%) (10-shot) | 12.6 |
| Open LLM Leaderboard v1 - MMLU | 26.42 | Accuracy (%) (5-shot) | 12.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 34.39 | Normalized accuracy (%) (25-shot) | 12.4 |
| Open LLM Leaderboard v1 - WinoGrande | 58.09 | Accuracy (%) (5-shot) | 11.3 |
| Open Portuguese LLM - OAB Exams | 23.1 | Accuracy (%) | 8.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.45 | MC2 (%) (0-shot) | 8.2 |
| Open Portuguese LLM - BLUEX | 18.64 | Accuracy (%) | 6.6 |
| Open Portuguese LLM - ENEM | 18.47 | Accuracy (%) | 5.8 |
Interactive version: theaggregate.ai/model?slug=tinyllama-coder-py-4bit-v10 · How It Works · Data refreshed daily, snapshot 2026-09-23.