Qwen3 8B: newer Qwen3-2507 family variants have shipped; this profile remains specific to the original Qwen3-8B

The OnAirToday AI Progress Tracker recorded a verified change to Alibaba's Qwen3 8B (version qwen3-8b): Newer Qwen3-2507 family variants have shipped; this profile remains specific to the original Qwen3-8B.

Qwen3-8B is Alibaba’s open-weight, text-only model with switchable thinking and non-thinking modes, multilingual support, and tool-use capabilities. This profile covers the original checkpoint, not newer Qwen3-2507 family releases or the separately trained DeepSeek-R1-0528-Qwen3-8B derivative.

What changed in this review:

• The OTIS Mock AIME 2024–25 result is not retained: Not yet confirmed by public reporting.
• Capability score 67 → 69
• Flaws and limitations updated

Teams building on 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/qwen3-8b.

References:

• https://huggingface.co/Qwen/Qwen3-8B
• https://qwenlm.github.io/blog/qwen3/
• https://arxiv.org/abs/2505.09388