A new study from Qwen finds that AI agents are less likely to complete tasks…

This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.

A new study from Qwen finds that AI agents are less likely to complete tasks successfully in low-resource languages, and can burn up to 2x more tokens in the process. Qwen just open-sourced BabelArena, a benchmark evaluating AI agents across 23 languages. Unlike benchmarks that only translate task statements, BabelArena localizes everything. Prompts, tool documentation, databases, and evaluators are all fully localized. This allows true apples-to-apples performance comparisons across languages. The benchmark spans 23 languages, 4 agent suites, and 13 domains. In total, it covers 702 standa

Posted by 智东西China AI News (2.9k followers) 1 h ago · 1 likes · 306 views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

• 🤯Dario无敌了！Fable 5.5 灰测炸裂：纯代码一发入魂，直接干翻所有生图/视频模型！吉卜力级动漫短片诞生！灰测指南务必码住！ — @NFT_Chen
• 美团发布 LongCat-2.5 正式版，距离今年 9 月预览版上线已有一个多月。 — @0xLogicrw
• Meet Ministral 3 14B Instruct 2512, abliterated and GGUF-ready. This uncensored 14B… — @HuggingModels
• 💥疯了！Qwen自己长出了一颗真GPU，在权重里跑真实CUDA！ — @NFT_Chen
• Made another tiny Claude Code mod: every GitHub PR link in the chat gets its status… — @adrianthedev
• 周末趁我们休息的时候，DeepSeek 又突然放出一个王炸：Super-agent（超级 Agent 系统）。 — @GitHub_Daily
• Meet Ministral 3 8B Instruct 2512, now in abliterated GGUF form. This uncensored,… — @HuggingModels
• 🫨简直无敌！DeepSeek Harness被清华微软团队直接“瘦身”：Token消耗砍掉87.93%，成功率反而暴涨14%！ — @NFT_Chen

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 10:27 UTC. Full method.