DataLearner logo
CO

CodeGeeX

Coding modelCodeGeeXCodeGeeX

CodeGeeX

Release date: 2022-09-30Updated: 2023-07-08 08:38:13.035859
Parameters
13B
Context length
2K
Chinese support
Supported
Reasoning ability

CodeGeeX is an AI model published by Zhipu AI, released on 2022-09-30, for Coding model, with 13B parameters, and 2K context length, with a 60.92 score on HumanEval pass@100.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

CodeGeeX

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Coding model
Modality (in / out)
No data
Release date
2022-09-30
Model file size
No data
MoE architecture
No
Total params / Active params
13B / N/A
Knowledge cutoff
No data
CodeGeeX

Open source & experience

Code license
Weights license
Proprietary
Live demo
No live demo
CodeGeeX

Official resources

Paper
DataLearnerAI blog
No blog post yet
CodeGeeX

API details

API speed
No data
No public API pricing yet.
CodeGeeX

Benchmark Results

CodeGeeX currently shows benchmark results led by HumanEval pass@10 (16 / 18, score 39.57), HumanEval (90 / 101, score 22.90), HumanEval pass@100 (20 / 21, score 60.92). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
22.90
90 / 101

Coding and Software Engineering

2 evaluations
Benchmark / mode
Score
Rank/total
HumanEval pass@100
Standard Mode
60.92
20 / 21
HumanEval pass@10
Standard Mode
39.57
16 / 18

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

CodeGeeX

Publisher

CodeGeeX

Model Overview

CodeGeeX is an AI model published by Zhipu AI, released on 2022-09-30, for Coding model, with 13B parameters, and 2K context length, with a 60.92 score on HumanEval pass@100.

Foundation model

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code