Kushindwa kwa kategoria za AI BENCHY
Ufuataji wa maagizo: Hakufuata maelekezo
Ufuataji wa maagizo
Hakufuata maelekezo
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Hakufuata maelekezo katika Ufuataji wa maagizo, ili uone udhaifu haraka. Panga kwa: Muda wa majibu (wastani) ↑.
Sababu za kushindwa
| Nafasi | Modeli | Kampuni | Idadi ya Hakufuata maelekezo | Alama ya kategoria | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #82 | Grok 4.20 none | X AI | 1 | 4.8 | 0/2 | 455ms |
| #79 | Grok 4.20 Beta none | X AI | 1 | 4.8 | 0/2 | 687ms |
| #96 | GPT-5.4 Nano none | OpenAI | 1 | 5.0 | 0/2 | 787ms |
| #60 | Gemma 4 26B A4B none | 1 | 4.4 | 0/2 | 1.08s | |
| #78 | Trinity Large Preview none | Arcee AI | 1 | 4.1 | 0/2 | 1.09s |
| #89 | GPT-4o-mini none | OpenAI | 1 | 4.8 | 0/2 | 1.27s |
| #88 | Nemotron 3 Super none | NVIDIA | 1 | 4.9 | 0/2 | 1.50s |
| #75 | GLM 5.1 none | Z.ai | 1 | 8.3 | 1/2 | 1.58s |
| #44 | GPT-5.4 Mini medium | OpenAI | 1 | 7.4 | 1/2 | 2.50s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 8.3 | 1/2 | 4.63s |
| #71 | MiniMax M2.5 medium | Minimax | 1 | 8.1 | 1/2 | 4.64s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 1 | 8.3 | 1/2 | 4.92s |
| #25 | Grok 4.20 Beta medium | X AI | 1 | 8.3 | 1/2 | 4.97s |
| #30 | Step 3.5 Flash medium | Stepfun | 1 | 8.5 | 1/2 | 4.98s |
| #84 | gpt-oss-120b none | OpenAI | 1 | 8.4 | 1/2 | 5.10s |