Kimi K2p5: clarified benchmark editions as AIME 2025 and Terminal-Bench 2.0
Tracker clarifies the benchmark versions associated with Kimi K2p5
Clarified benchmark editions as AIME 2025 and Terminal-Bench 2.0 — verified by the OnAirToday AI Progress Tracker against Moonshot's published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to Moonshot's Kimi K2p5 (version kimi-k2.5): Clarified benchmark editions as AIME 2025 and Terminal-Bench 2.0.
Kimi K2.5 is Moonshot AI’s open-weight multimodal model for text generation, image and video understanding, coding, and tool-assisted workflows. Its standalone model capabilities should be distinguished from the execution infrastructure and Agent Swarm orchestration available through the Kimi product.
What changed in this review:
- Removed OTIS Mock AIME and FrontierMath figures without established model-specific published attribution.
- Separated the reported Kimi K3 Redis exploit case from Kimi K2.5 vulnerabilities.
- Capability score 68 → 70
- Risks and threats updated
Teams building on Kimi K2p5 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/kimi-k2p5.
References:
- https://huggingface.co/moonshotai/Kimi-K2.5
- https://platform.moonshot.ai/docs/pricing/chat
Generated insight by OnAirToday AI
Naming the benchmark editions makes the reported results more precise and easier to compare with evaluations using the same versions. The clarification also ties the tracker’s entries to Moonshot’s published documentation.

Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.