tinyllama-coder-py-v12: benchmark results
Provider: Singapore Univ. Access: Open.
Unified ELO 1224 ± 20, rank #2858 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 50.02 | Macro F1 (%) | 31.9 |
| Open LLM Leaderboard v1 - GSM8K | 1.44 | Accuracy (%) (5-shot) | 17 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.91 | MC2 (%) (0-shot) | 15.6 |
| Open LLM Leaderboard v1 - MMLU | 26.31 | Accuracy (%) (5-shot) | 12.2 |
| Open LLM Leaderboard v1 - HellaSwag | 53.61 | Normalized accuracy (%) (10-shot) | 11.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 32 | Normalized accuracy (%) (25-shot) | 10.8 |
| Open Portuguese LLM - ASSIN2 RTE | 36.54 | Macro F1 (%) | 10.5 |
| Open LLM Leaderboard v1 - WinoGrande | 57.06 | Accuracy (%) (5-shot) | 10.3 |
| Open Portuguese LLM - OAB Exams | 10.34 | Accuracy (%) | 4.1 |
| Open Portuguese LLM - ENEM | 10.29 | Accuracy (%) | 3.6 |
| Open Portuguese LLM - BLUEX | 2.78 | Accuracy (%) | 3 |
Interactive version: theaggregate.ai/model?slug=tinyllama-coder-py-v12 · How It Works · Data refreshed daily, snapshot 2026-09-23.