Home/Models/DeepSeek Coder 6.7B
DeepSeek logo

DeepSeek Coder 6.7B

by DeepSeek · Released Jan 2024

Open Source
16.1
avg score
Rank #213
Compare
Better than 9% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Open Source
Benchmarks
4 tested
Data updated today
About

Tested on 4 benchmarks with 16.7% average. Top scores: GSM8K (21.3%), ARC AI2 (15.2%), MMLU (15.2%).

Capabilities
math
21.3
#155 globally
knowledge
15.2
#204 globally
Benchmark Scores
Compare All
Tested on 4 benchmarks · Ranked across 2 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
GSM8K

Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.

21.3
ARC AI2

AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.

15.2
MMLU

Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.

15.2
Winogrande

Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.

15.2
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
deepseek-coder-6-7b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
DeepSeek logoDeepSeekTBD
Categories
Share & Export
Tweet
DeepSeek Coder 6.7B is an open-source text AI model by DeepSeek, released in January 2024. It has an average benchmark score of 16.1.