Deepseek R1 0528 Qwen3 8b: clarified that the 86.0% mathematics result is AIME 2024

The OnAirToday AI Progress Tracker recorded a verified change to Deepseek R1 0528 Qwen3 8b (version DeepSeek-R1-0528-Qwen3-8B): Clarified that the 86.0% mathematics result is AIME 2024.

DeepSeek-R1-0528-Qwen3-8B is an open-weight, text-only reasoning model distilled from DeepSeek-R1-0528 into the Qwen3-8B architecture. Its published evaluations emphasize mathematics, scientific reasoning and coding; it is a distinct checkpoint, not an interchangeable name for DeepSeek’s hosted reasoning service.

What changed in this review:

• Added the published AIME 2025 result of 76.3%.
• Documented the January 2025 DeepSeek infrastructure exposure, explicitly distinguishing it from a vulnerability in this later checkpoint.
• Capability score 64 → 71
• Flaws and limitations updated
• Risks and threats updated

Teams building on Deepseek R1 0528 Qwen3 8b 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/deepseek-r1-0528-qwen3-8b.

References:

• https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
• https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/main/config.json
• https://github.com/deepseek-ai/DeepSeek-R1
• https://www.wiz.io/blog/wiz-research-uncovers-exposed-deepseek-database-leak-sensitive-information