bigyi-15B: benchmark results
Abacus.AI's bigyi-15b, a passthrough mergekit upscale of 01-ai's Yi-9B into a larger base completion model with a 4K context and no chat template. Provider: Abacus.AI. Released 2024-03-06. Access: Open.
Aggregate Rating 1313 ± 18, rank #1453 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - C-Eval Semantic | 78.47 | Accuracy (%) | 68 |
| Open LLM Leaderboard - GPQA | 30.96 | Score | 67.1 |
| Open Chinese LLM - CMMLU | 57.47 | Accuracy (%) | 64.2 |
| Open Portuguese LLM - OAB Exams | 45.79 | Accuracy (%) | 62.3 |
| Open Portuguese LLM - ENEM | 62.98 | Accuracy (%) | 54.1 |
| Open Chinese LLM - ARC Challenge | 52.65 | Accuracy (%) | 50.4 |
| Open Portuguese LLM - BLUEX | 51.74 | Accuracy (%) | 50.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Chinese LLM - HellaSwag | 59.39 | Accuracy (%) | 43.8 |
| Open Portuguese LLM - FaQuAD NLI | 57.21 | Macro F1 (%) | 40.5 |
| Open Chinese LLM - WinoGrande | 62.27 | Accuracy (%) | 39.8 |
| Open LLM Leaderboard - MMLU-Pro | 30.03 | Score | 36.3 |
Interactive version: theaggregate.ai/model?slug=bigyi-15b · How It Works · Data refreshed daily, snapshot 2026-10-20.