NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/DeepSeek Coder 33B
DeepSeek logo

DeepSeek Coder 33B

by DeepSeek · Released Jan 2024

Open Source
27.3
avg score
Rank #259
Compare
Better than 17% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Open Source
Benchmarks
4 tested
Data as of
About

Tested on 4 benchmarks · BenchGecko score 27.3. Top scores: GSM8K (35.4%), Winogrande (24.0%), ARC AI2 (22.9%).

Capabilities
math
35.4
#172 globally
knowledge
22.0
#260 globally
Benchmark Scores
Compare All
Tested on 4 benchmarks · Ranked across 2 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
mathCompare math →
GSM8K

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

35.4·
knowledgeCompare knowledge →
Winogrande

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

24.0·
ARC AI2

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

22.9·
MMLU

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

19.2·
Quick compare:OpenAI logovs GPT-4o-miniz-ai logovs GLM 4.6VAlibaba logovs Qwen2.5 1.5B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
OpenAI logo
GPT-4o-mini
OpenAI
27.5$0.15/1M
z-ai logo
GLM 4.6V
z-ai
27.7$0.30/1M
Alibaba logo
Qwen2.5 1.5B Instruct
Alibaba
26.8n/a
Links
Info
DeepSeekPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@DeepSeek
Source Code
GitHubHugging Face
BenchGecko API
deepseek-coder-33b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
DeepSeek logoDeepSeekn/a
Categories
mathknowledge
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
OpenAI logoGPT-4o-mini
27.5
z-ai logoGLM 4.6V
27.7
Alibaba logoQwen2.5 1.5B Instruct
26.8
OpenAI logoGPT-5.4 Nano
28.1
DeepSeek Coder 33B is an open-source text AI model by DeepSeek, released in January 2024. It has an average benchmark score of 27.3.

Related Models

GPT-4o-mini · OpenAIGLM 4.6V · z-aiQwen2.5 1.5B Instruct · AlibabaGPT-5.4 Nano · OpenAIClaude 3 Opus · Anthropic

Benchmarks

GSM8KWinograndeARC AI2MMLU

Related Pages

DeepSeek · ProviderDeepSeek · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • DeepSeek Coder 33B by DeepSeek. BenchGecko score 27.3, rank 259 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

DeepSeek Coder 33B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/deepseek-coder-33b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP