dolphin-2.9.1-llama-3-70B — benchmark results
Eric Hartford's Cognitive Computations uncensored Dolphin fine-tune of Llama 3 70B with agentic and function-calling abilities. Provider: Cognitive Computations. Released 2024-05-22. Access: Open.
Unified ELO 1490 ± 27, rank #841 of 1776 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 23.7 | Score | 98.5 |
| Open Chinese LLM - GSM8K | 70.96 | Accuracy (%) | 97.6 |
| Open Chinese LLM - CMMLU | 72.34 | Accuracy (%) | 96.1 |
| Open Chinese LLM Leaderboard | 68.63 | Average Score (%) | 92.3 |
| Open Chinese LLM - ARC Challenge | 60.49 | Accuracy (%) | 88.9 |
| Open Chinese LLM - HellaSwag | 67.85 | Accuracy (%) | 85.2 |
| Open Chinese LLM - WinoGrande | 67.72 | Accuracy (%) | 84.9 |
| Open Chinese LLM - C-Eval Semantic | 87.12 | Accuracy (%) | 83.7 |
| Open LLM Leaderboard - MMLU-Pro | 34.78 | Score | 75.2 |
| Open LLM Leaderboard - MATH Level 5 | 18.2 | Score | 67.8 |
| Open LLM Leaderboard - GPQA | 7.83 | Score | 66.2 |
| Open LLM Leaderboard - BBH | 31.1 | Score | 55.6 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-9-1-llama-3-70b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.