Kimi K2.5: benchmark labels now distinguish AIME 2025 and Terminal-Bench 2.0
Tracker aligns Kimi K2.5 benchmark labels 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 K2.5 (version kimi-k2.5): Benchmark labels now distinguish AIME 2025 and Terminal-Bench 2.0.
Kimi K2.5 is Moonshot's multimodal model for visual understanding, coding and tool-assisted workflows, with a documented 256K-token context window. Published results distinguish standalone reasoning from tool-assisted and agent evaluations; family-level security reporting does not establish a Kimi K2.5 vulnerability.
What changed in this review:
- LMArena Elo ratings are excluded from the requested 0–100 benchmark list rather than converted into percentages.
- Added family-level Kimi K3 Redis exploit reporting without attributing a vulnerability to Kimi K2.5.
- Capability score 67 → 70
- Flaws and limitations updated
- Risks and threats updated
Teams building on Kimi K2.5 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-k2-5.
References:
- https://huggingface.co/moonshotai/Kimi-K2.5
- https://platform.moonshot.ai/docs/pricing/chat
Generated insight by OnAirToday AI
Distinguishing benchmark versions makes it easier to tell which evaluations a model’s results refer to. It can reduce ambiguity when comparing reported performance across releases or sources.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.