Qwen2.5-Max
A proprietary large-scale mixture-of-experts model trained on more than 20 trillion tokens and deployed through Qwen Chat and Alibaba Cloud's compatible API.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 66.4
Frontier-comparable general and coding evaluations support high capability, while chat search, artifacts and API integration provide moderate tool-mediated autonomy. Immediate cloud and chat access creates high deployment; closed hosting preserves stronger provider control than open-weight peers but widespread API access sustains meaningful misuse potential.
News tied to Qwen2.5-Max
The model score of 66.4 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Alibaba deploys Qwen2.5-Max through chat and API
Alibaba released Qwen2.5-Max, a large mixture-of-experts model pretrained on more than 20 trillion tokens, through Qwen Chat and the Alibaba Cloud API.
- Full item contribution
- +0.14
- Qwen2.5-Max equal share
- +0.14
Model score history
-
R3
Doom Score 66.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 67.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 69.8
Initial exact source-backed profile for the hosted Qwen2.5-Max API and chat release.
12 Aug 2026