Uandishi wa msimbo: Hakufuata maelekezo
Uandishi wa msimbo
Hakufuata maelekezo
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Hakufuata maelekezo katika Uandishi wa msimbo, ili uone udhaifu haraka.
Sababu za kushindwa
38/38
Chuja miundo
Hakuna miundo inayolingana na utafutaji na vichujio vya sasa.
| Nafasi | Modeli | Kampuni | Idadi ya Hakufuata maelekezo | Alama ya kategoria | Jumla ya gharama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|
| #365 | Qwen3.5-9B medium | Qwen | 1 | 0.3 | $0.106 | 0/3 | 100.9s |
| #368 | Grok 4.1 Fast medium | X AI | 1 | 0.8 | $0.069 | 0/1 | 23.6s |
| #369 | Laguna M.1 medium | Poolside | 1 | 0.1 | $0.033 | 0/1 | 35.6s |
| #371 | Granite 4.1 8b default | IBM Granite | 1 | 0.4 | $0.007 | 0/3 | 775ms |
| #373 | Ling 3.0 Tiny high | Inclusionai | 1 | 0.3 | $0.000 | 0/3 | 177.7s |
| #374 | Ling 3.0 Tiny low | Inclusionai | 1 | 0.3 | $0.000 | 0/3 | 170.7s |
| #375 | Ling 3.0 Tiny medium | Inclusionai | 1 | 0.3 | $0.000 | 0/3 | 212.0s |
| #385 | MiMo-V2-Flash default | Xiaomi | 1 | 0.4 | $0.025 | 0/3 | 2.64s |