Kimi K2p5: benchmark labels now distinguish AIME 2025 and Terminal-Bench 2.0
Tracker aligns benchmark names with Moonshot documentation
Benchmark labels now distinguish 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): Benchmark labels now distinguish AIME 2025 and Terminal-Bench 2.0.
Kimi K2.5 is Moonshot AI’s open-weight multimodal model for text generation, coding, and image and video understanding. Its documented configuration includes a 256K-token context window, with listed API prices of $0.60 per million input tokens and $3.00 per million output tokens.
What changed in this review:
- Removed FrontierMath and OTIS figures lacking result-specific citations.
- Separated the reported K3 Redis research demonstration from claims of a K2.5 vulnerability or production breach.
- Capability score 68 → 70
- Flaws and limitations updated
- 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
Precise benchmark labels make model evaluations easier to interpret and compare. Verification against Moonshot's documentation helps readers trace the distinctions to a published source.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.