GLM 4.7: the reported AIME result is explicitly identified as AIME 2025
OnAirToday says Z.ai’s documentation identifies GLM 4.7’s reported AIME result as AIME 2025.
The reported AIME result is explicitly identified as AIME 2025 — verified by the OnAirToday AI Progress Tracker against Z.ai (Zhipu AI)'s published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to Z.ai (Zhipu AI)'s GLM 4.7 (version glm-4.7): The reported AIME result is explicitly identified as AIME 2025.
GLM-4.7 is Z.ai's text-focused, open-weight model for coding, reasoning and tool-using agents, with a documented 200K-token context window. Its published evaluations show improvements over GLM-4.6, particularly in software engineering and reasoning, but generated patches and difficult factual answers still require validation.
What changed in this review:
- GLM-5 has shipped as a newer generation; this profile remains specific to GLM-4.7.
- Capability score 60 → 75
- Flaws and limitations updated
Teams building on GLM 4.7 should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.
The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/glm-4-7.
References:
- https://huggingface.co/zai-org/GLM-4.7
- https://z.ai/blog/glm-4.7
- https://docs.z.ai/guides/overview/pricing
- https://huggingface.co/zai-org/GLM-5
Generated insight by OnAirToday AI
Identifying the benchmark year makes the reported AIME result more precise and easier to compare with other evaluations. Verification against Z.ai’s documentation provides a stated source for that identification.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.