bigyi-15B: benchmark results
Provider: Other. Released 2024-03-06. Access: Open.
Unified ELO 1363 ± 1, rank #1236 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - C-Eval Semantic | 78.47 | Accuracy (%) | 68 |
| Open LLM Leaderboard - GPQA | 7.94 | Score | 67.1 |
| Open Chinese LLM - CMMLU | 57.47 | Accuracy (%) | 64.1 |
| Open Chinese LLM - ARC Challenge | 52.65 | Accuracy (%) | 50.6 |
| Open Chinese LLM - HellaSwag | 59.39 | Accuracy (%) | 43.9 |
| Open Chinese LLM - WinoGrande | 62.27 | Accuracy (%) | 39.9 |
| Open LLM Leaderboard - MMLU-Pro | 22.25 | Score | 36.4 |
| Open Chinese LLM Leaderboard | 53.23 | Average Score (%) | 30 |
| Open LLM Leaderboard - BBH | 19.94 | Score | 29.9 |
| Open LLM Leaderboard - MuSR | 4.29 | Score | 21.1 |
| Open LLM Leaderboard - MATH Level 5 | 2.95 | Score | 18.6 |
| Open Korean LLM Leaderboard | 31.31 | Average Score (%) | 14.9 |
Interactive version: theaggregate.ai/model?slug=bigyi-15b · How It Works · Data refreshed daily, snapshot 2026-09-05.