Claude Opus 5 vs GLM-5.3

Claude Opus 5 (Anthropic) and GLM-5.3 (Zhipu AI (Z.ai)) compared on price, context window, speed and independent benchmarks. Claude Opus 5 scores higher on the Artificial Analysis Intelligence Index (63.1 vs 59.5), while GLM-5.3 is 4.7× cheaper on a blended basis. Pick Claude Opus 5 for the hardest tasks and GLM-5.3 when cost dominates.

Claude Opus 5GLM-5.3
ProviderAnthropicZhipu AI (Z.ai)
Input $/1M$5.00$1.40
Output $/1M$25.0$4.40
Blended $/1M (3:1)$10.0$2.15
Cached input $/1M$0.50$0.26
Context window1M1M
Knowledge cutoff2026-05
Licenseproprietaryopen weights
Speed (tok/s)5278
Artificial Analysis Intelligence Index63.159.5
LMArena Elo15051474
GPQA Diamond93.2%91.7%
SWE-bench Verified97%
LiveCodeBench74.6%
MMLU-Pro91.6%
Humanity's Last Exam54.9%42.3%

← Interactive comparison (pick any 4 models)