๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Paweล‚ Huryn
@PawelHuryn
AI PM | Deep research. I build, test, then teach. 141K+ subscribe โ†’
๊ฐ€์ž… November 2021
447 ํŒ”๋กœ์ž‰ ์ค‘    135.5K ํŒฌ
So I tested DeepSeek V4.1 Flash 1017 on real work. 2 repos. 105 hidden bugs. Find and fix what you can. The first results: Muse Wonder Full 1.0 (max): 42 Opus 5.5 (max): 41.7 Gemini 4 Argon (high): 40.7 DeepSeek V4.1 Flash 1017 (max): 34 ๐ŸŸฃ Grok 4.7 (xhigh): 29 Qwen3.8-Max (max): 25.7 DeepSeek V4.1 Flash (max): 21.7 ๐ŸŸฃ GLM-5.3 (max): 19 A great improvement. Strange that the model wasn't labeled V4.2. 763B params. The weights are already on Hugging Face. I expect the score to change by ~1.7 points after repeating the test 3 times. More data and results at different effort levels dropping in this thread very soon ๐Ÿงต
๋” ๋ณด๊ธฐ