聯想天禧 AI 自研程式碼代理框架 TianxiCode 搭配 DeepSeek V4.1 Flash,在 2026 年 10 月 8 日的 SWE bench Live Lite 榜單上解決 300 項任務中的 213 項,取得官方核驗的 71% 解題率並排名第一。
第二名的已核驗項目得分為 70.33%,兩者差距約 0.67 個百分點;這項結果只適用於 Lite 分榜,不能據此推論其在完整榜或多語言榜領先。
SWE bench Live 以真實 GitHub 專案問題測試 AI 系統修復程式碼的能力;此次分數反映 DeepSeek 模型與 TianxiCode 框架的整體表現,而非單一模型的成績。
What did Lenovo’s Tianxi AI team achieve with its in-house TianxiCode coding-agent framework running DeepSeek-V4.1-Flash on SWE-bench-Live LTianxiCode paired with DeepSeek-V4.1-Flash scored 71% on SWE-bench-Live Lite.
AI 提示詞
Create a landscape editorial hero image for this Studio Global article: What did Lenovo’s Tianxi AI team achieve with its in-house TianxiCode coding-agent framework running DeepSeek-V4.1-Flash on SWE-bench-Live L. Article summary: Lenovo’s Tianxi AI team reportedly took first place on SWE-bench-Live Lite with its in-house TianxiCode agent framework running DeepSeek-V4.1-Flash, achieving an officially verified 71% resolution rate; QbitAI reported t. Topic tags: general, general web, user generated. Style: premium digital editorial illustration, source-backed research mood, clean composition, high detail, modern web publication hero. Use reference image context only for broad subject, composition, and topical grounding; do not copy the exact image. Avoid: logos, brand marks, copyrighted characters, real person likenesses, fake screenshots, UI text, readable text, watermarks, charts with fa
聯想天禧 AI 自研程式碼代理框架 TianxiCode 搭配 DeepSeek V4.1 Flash,在 2026 年 10 月 8 日的 SWE bench Live Lite 榜單上解決 300 項任務中的 213 項,取得官方核驗的 71% 解題率並排名第一。
第二名的已核驗項目得分為 70.33%,兩者差距約 0.67 個百分點;這項結果只適用於 Lite 分榜,不能據此推論其在完整榜或多語言榜領先。
SWE bench Live 以真實 GitHub 專案問題測試 AI 系統修復程式碼的能力;此次分數反映 DeepSeek 模型與 TianxiCode 框架的整體表現,而非單一模型的成績。
What did Lenovo’s Tianxi AI team achieve with its in-house TianxiCode coding-agent framework running DeepSeek-V4.1-Flash on SWE-bench-Live LTianxiCode paired with DeepSeek-V4.1-Flash scored 71% on SWE-bench-Live Lite.
AI 提示詞
Create a landscape editorial hero image for this Studio Global article: What did Lenovo’s Tianxi AI team achieve with its in-house TianxiCode coding-agent framework running DeepSeek-V4.1-Flash on SWE-bench-Live L. Article summary: Lenovo’s Tianxi AI team reportedly took first place on SWE-bench-Live Lite with its in-house TianxiCode agent framework running DeepSeek-V4.1-Flash, achieving an officially verified 71% resolution rate; QbitAI reported t. Topic tags: general, general web, user generated. Style: premium digital editorial illustration, source-backed research mood, clean composition, high detail, modern web publication hero. Use reference image context only for broad subject, composition, and topical grounding; do not copy the exact image. Avoid: logos, brand marks, copyrighted characters, real person likenesses, fake screenshots, UI text, readable text, watermarks, charts with fa