Kazi za mawakala: Jibu lisilo sahihi
Kazi za mawakala
Jibu lisilo sahihi
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Jibu lisilo sahihi katika Kazi za mawakala, ili uone udhaifu haraka. Panga kwa: Jumla ya gharama ↑.
Sababu za kushindwa
108/108
Chuja miundo
Hakuna miundo inayolingana na utafutaji na vichujio vya sasa.
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama ya kategoria | Jumla ya gharama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|
| #173 | Space Bunny Alpha max | Stealth | 1 | 6.1 | $0.000 | 0/1 | 90.6s |
| #210 | Dots 3 Note Preview high | Dots Studio | 1 | 6.1 | $0.000 | 0/1 | 129.1s |
| #211 | Dots 3 Note Preview low | Dots Studio | 1 | 6.1 | $0.000 | 0/1 | 161.2s |
| #221 | Space Bunny Alpha medium | Stealth | 1 | 6.1 | $0.000 | 0/1 | 153.1s |
| #257 | Dots 3 Note Preview medium | Dots Studio | 1 | 4.7 | $0.000 | 0/1 | 140.5s |
| #259 | Space Bunny Alpha low | Stealth | 1 | 4.7 | $0.000 | 0/1 | 89.0s |
| #273 | North Mini Code medium | Cohere | 1 | 3.9 | $0.000 | 0/1 | 105.2s |
| #299 | Dots 3 Note Preview none | Dots Studio | 1 | 3.9 | $0.000 | 0/1 | 45.7s |
| #316 | North Mini Code none | Cohere | 1 | 3.0 | $0.000 | 0/1 | 18.9s |
| #272 | Qwen3.8 27B none | Qwen | 1 | 5.0 | ~$0.010 | 0/1 | 47.4s |
| #297 | Mercury 2.5 Preview low | Inception | 1 | 5.0 | $0.015 | 0/1 | 84.5s |
| #342 | gpt-oss-120b none | OpenAI | 1 | 6.1 | $0.016 | 0/1 | 140.9s |
| #333 | Nemotron 3 Super none | NVIDIA | 1 | 2.8 | $0.016 | 0/1 | 30.5s |
| #300 | GPT-4o-mini none | OpenAI | 1 | 5.0 | $0.024 | 0/1 | 40.0s |
| #268 | Gemma 4 26B A4B none | 1 | 5.0 | $0.026 | 0/1 | 75.8s |