Compare AI models

Specifications
Parameters
128B9B/32B
Context window
256k128k
API pricing
Input price
$1.50$0.1032B checkpoint
Output price
$7.50$0.10
Cached input price
$0.15—
Cheapest input
$1.50Mistral—
Cheapest output
$7.50Mistral—
$675Mistral list price$25.00Z.ai list price
Benchmarks
SWE-Bench Verified
77.6%27.2%
Overview
CompanyMistralZ.ai
Release dateApr 28 2026Apr 14 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3.5 leads GLM-4-0414 on 1 of the 1 benchmark they both report (SWE-Bench Verified). GLM-4-0414 is cheaper on both input and output: $0.10 vs $1.50 per million input tokens, and $0.10 vs $7.50 per million output tokens. The listed GLM-4-0414 rates use the “32B checkpoint” pricing scope. GLM-4-0414 shipped 379 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.

Mistral Medium 3.5 has 128B parameters, while GLM-4-0414 has 9B/32B. Context windows are 256k (Mistral Medium 3.5) vs 128k (GLM-4-0414).

On SWE-Bench Verified, Mistral Medium 3.5 leads at 77.6% vs GLM-4-0414 at 27.2%.