dolphin-2.9.3-Yi-1.5-34B-32k: benchmark results
Cognitive Computations' uncensored Dolphin 2.9.3 fine-tune of Yi 1.5 34B 32k with instruction, coding, agentic and function-calling data. Provider: Cognitive Computations. Released 2024-06-23. Access: Open.
Aggregate Rating 1564 ± 44, rank #1500 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - C-Eval Semantic | 89.16 | Accuracy (%) | 90.5 |
| Open Chinese LLM - WinoGrande | 69.38 | Accuracy (%) | 90.1 |
| Open Chinese LLM - CMMLU | 70.68 | Accuracy (%) | 87.9 |
| Open Chinese LLM - GSM8K | 61.33 | Accuracy (%) | 86.1 |
| Open LLM Leaderboard - GPQA | 34.31 | Score | 85.4 |
| Open LLM Leaderboard - MMLU-Pro | 46.3 | Score | 85.2 |
| Open Chinese LLM - HellaSwag | 67.03 | Accuracy (%) | 82.8 |
| Open LLM Leaderboard - BBH | 60.47 | Score | 82.4 |
| Open Chinese LLM Leaderboard | 63.96 | Official Nonzero-Task Mean (%) | 78.4 |
| Open Chinese LLM - ARC Challenge | 57.51 | Accuracy (%) | 75.3 |
| Open LLM Leaderboard - MuSR | 43.11 | Score | 71.3 |
| Open LLM Leaderboard - MATH Level 5 | 16.69 | Score | 65 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-9-3-yi-1-5-34b-32k · How It Works · Data refreshed daily, snapshot 2026-11-08.