Better than 62% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-generation
License
Open Source
Benchmarks
6 tested
Data updated today
About
Dphn text generation model. 4522K downloads on HuggingFace.
Tested on 6 benchmarks with 28.3% average. Top scores: BBH (HuggingFace) (44.2%), MMLU-PRO (39.1%), IFEval (38.5%).
Capabilities
reasoning
17.0
#105 globally
math
18.7
#167 globally
knowledge
25.8
#184 globally
language
38.5
#115 globally
general
44.2
#15 globally
Benchmark Scores
Compare AllTested on 6 benchmarks · Ranked across 5 categories
Score Distribution (all 231 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR
17.0—HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.
mathCompare math →
MATH Level 5
18.7—HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.
knowledgeCompare knowledge →
MMLU-PRO
39.1—HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.
GPQA
12.4—HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.
vs Qwen2.5 Coder 7B Instruct
vs GPT-4 Turbo Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
dphn-dolphin-291-yi-15-34b
Specifications
- Typetext-generation
- ContextN/A
- ReleasedMay 2024
- LicenseOpen Source
- StatusActive
Available On
D
DPHNTBDLearn More
Share & Export
Frequently Asked Questions
Dolphin 2.9.1 Yi 1.5 34b is an open-source text-generation AI model by DPHN, released in May 2024. It has an average benchmark score of 55.9.