ModelsCompareBest forBenchmarksStatusPricingAPI

GLM-5

Z.ai·Pendingtext
Context200k
Max output131.072k
Input / 1M$1 ↗
Output / 1M$3.2 ↗
Cached in$0.2
Benchmarks8

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

AIME 2025 (MathArena)#3/2396.7% ↗
AIME 2026 (MathArena)#6/2196.7% ↗
GPQA Diamond (Epoch AI run)#36/7787.8% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#53/7680% ↗
SWE-bench Verified (Epoch AI run)#14/2472.1% ↗
LMArena Elo#19/621446.3 ↗
SWE-bench Verified#9/4577.8% ↗
Terminal-Bench 2.0#6/1356.2% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Z.ai

GLM-5.3GLM-5.3-FlashGLM-5.2GLM-4.7-FlashXGLM-5.1GLM-5-Turbo

Access GLM-5 and every other model through one endpoint with automatic failover: Respan gateway.