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
—$0.40DeepInfra
Cheapest output
—$1.60DeepInfra
—$174Venice · fp4
Benchmarks
LiveCodeBench
74.1%82.8%
AIME 2025
92.3%93.9%
GPQA Diamond
81.1%81%
MMLU-Pro
84.4%83.2%
Overview
CompanyQwenZ.ai
Release dateJul 21 2025Sep 30 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 and GLM-4.6 are evenly matched across the 4 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond, MMLU-Pro). Only GLM-4.6 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 71 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.

Qwen3-2507 has 4B/30B/235B parameters, while GLM-4.6 has 355B. Context windows are 256k (Qwen3-2507) vs 200k (GLM-4.6).

On LiveCodeBench, GLM-4.6 leads at 82.8% vs Qwen3-2507 at 74.1%. On AIME 2025, GLM-4.6 leads at 93.9% vs Qwen3-2507 at 92.3%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs GLM-4.6 at 81%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs GLM-4.6 at 83.2%.