Me: deepseek, glm, kimi, battle formation...., F blender we are going in!
(friendslop showcase:)
DeepSeek Harness vs Claude Code: the free harness hit 105,000 GitHub stars in 2 days.
One of the fastest growing GitHub projects of all time. So we tested it head to head. Same prompt. Same task. Build a 3D accountancy website plus a Tetris game. → DeepSeek: finished in 11
DeepSeek V4 Flash: the free model that beats its own Pro version.
Same architecture. Same parameter count. DeepSeek just retrained it. Now it wins on all 9 agent benchmarks against the bigger paid model. → DeepSWE: jumped from 7.3 to 54.4 on the SAME model → Terminal Bench:
Grok 4.6 ranks #1 on RuntimeWire’s Newsroom Reliability v0.2 benchmark with a score of 0.79
Beating GPT-5.6 Sol, Claude Opus 4.8, Gemini and DeepSeek.
You have reached the end of the archive
All of deepseek