Compare AI models

Specifications
Parameters
4B/30B/235B355B
Context window
256k200k
API pricing
Input price
—$0.60
Output price
—$2.20
Cached input price
—$0.11
Cheapest input
—$0.32DeepInfra
Cheapest output
—$1.40DeepInfra
—$168DeepInfra · fp4
Benchmarks
LiveCodeBench
74.1%84.9%
Humanity's Last Exam · text only, no tools
18.2%24.8%
AIME 2025
92.3%95.7%
GPQA Diamond
81.1%85.7%
MMLU-Pro
84.4%84.3%
Overview
CompanyQwenZ.ai
Release dateJul 21 2025Dec 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.7 leads Qwen3-2507 on 4 of the 5 benchmarks they both report. Only GLM-4.7 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3-2507. Qwen3-2507 shipped 154 days before GLM-4.7, so benchmark comparisons should account for the intervening progress.

Qwen3-2507 has 4B/30B/235B parameters, while GLM-4.7 has 355B. Context windows are 256k (Qwen3-2507) vs 200k (GLM-4.7).

On LiveCodeBench, GLM-4.7 leads at 84.9% vs Qwen3-2507 at 74.1%. On Humanity's Last Exam · text only, no tools, GLM-4.7 leads at 24.8% vs Qwen3-2507 at 18.2%. On AIME 2025, GLM-4.7 leads at 95.7% vs Qwen3-2507 at 92.3%. On GPQA Diamond, GLM-4.7 leads at 85.7% vs Qwen3-2507 at 81.1%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs GLM-4.7 at 84.3%.