#22
GLM-5
Z.AI · Open Weight · Non-Reasoning · 200K context
63/ 100 composite
Released 2026-03-01
Benchmark Scores by Category
Coding
59.4
Knowledge
77.9
Reasoning
81.2
Agentic
43.7
Math
57.2
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$1
per 1M tokens
Output
$3.2
per 1M tokens
Value Score
20.4
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: