z-ai/glm-5.1GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.
Scores on standardized evaluations. Higher is better — and rank shows where GLM-5.1 lands among all models tracked on Model Beat.
Graduate-level scientific reasoning
Common-sense trick questions
Factual accuracy & hallucination
Novel ML problem-solving
Real GitHub issue resolution
Human-rated web development
Olympiad-qualifier math
Research-level math problems
Hardest research math
Model & benchmark data from Epoch AI (CC BY); pricing, specs & descriptions from OpenRouter.