chiprook
← AI
AIOctober 10, 2026, 09:37

Lenovo's TianxiCode Agent Tops SWE-bench-Live Lite at 71%, Verified

Lenovo's TianxiCode coding agent, running DeepSeek-V4.1-Flash, resolved 71% of tasks on the SWE-bench-Live Lite leaderboard — 213 of 300 — and passed official verification. The margin over the next verified entry is narrow at 70.33%. The result applies to the Lite split only.

Lenovo's TianxiCode Agent Tops SWE-bench-Live Lite at 71%, Verified
#Lenovo#DeepSeek
Read next
Gaming

Krafton preps BGMI LITE in India: ~1 GB size, pre-registration live on Google Play

Policy

Moca Chain mainnet goes live to give AI agents verifiable identity

AI

Viedraft's Darwin-180B-RSI Tops 10 Categories on Hugging Face Leaderboard

AI

Benchmark: top LLMs know only 24% of post-cutoff 2025-2026 facts