#09Z.ai· released 2026-06-16

Z.ai: GLM 5.2.

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$0.95
Output $/1M
$2.98
Modality
text

Benchmarks

How these are aggregated →
Arena Elo
1518
LMArena — human blind votes
AA Index
66.0
Artificial Analysis composite
LiveBench
79.4
Contamination-resistant
GPQA
86.9%
Grad-level science reasoning
MMLU-Pro
87.8%
Broad knowledge
SWE-bench
73.6%
Real GitHub bugs (Verified)
Terminal-Bench
51.8%
Agentic shell tasks
ARC-AGI
18.9%
Abstract reasoning
Aider Polyglot
81.9%
Multi-language code editing
Speed
74 tok/s
Median output speed

Nearby on the leaderboard