Compare AI models

Specifications
Parameters
480B9B
Context window
256k128k
API pricing
Cheapest input
$0.35Venice—
Cheapest output
$1.50Venice—
$145Venice · fp8—
These models have no shared benchmark scores.
Overview
CompanyQwenZ.ai
Release dateJul 22 2025Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-Coder and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX4-ALL-9B shipped 382 days before Qwen3-Coder, so benchmark comparisons should account for the intervening progress.

Qwen3-Coder has 480B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 256k (Qwen3-Coder) vs 128k (CodeGeeX4-ALL-9B).

Direct benchmark comparisons are unavailable — Qwen3-Coder and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.