Kushindwa kwa kategoria za AI BENCHY
Utatuzi wa mafumbo: Jibu lisilo sahihi
Utatuzi wa mafumbo
Jibu lisilo sahihi
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Jibu lisilo sahihi katika Utatuzi wa mafumbo, ili uone udhaifu haraka.
Sababu za kushindwa
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama ya kategoria | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #122 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | 1/3 | 1.20s |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 1 | 6.7 | 1/3 | 1.30s |
| #125 | GPT-5.4 none | OpenAI | 1 | 5.6 | 1/3 | 1.44s |
| #126 | gpt-oss-120b none | OpenAI | 1 | 6.0 | 1/3 | 8.21s |
| #129 | MiniMax M2.5 medium | Minimax | 1 | 5.3 | 1/3 | 11.2s |
| #130 | MiniMax M2.7 medium | Minimax | 1 | 5.9 | 1/3 | 24.9s |
| #134 | GLM 5 Turbo none | Z.ai | 1 | 5.5 | 1/3 | 2.65s |
| #136 | Elephant Alpha medium | Openrouter | 1 | 5.3 | 1/3 | 868ms |
| #139 | DeepSeek V4 Flash none | DeepSeek | 1 | 3.1 | 0/3 | 23.7s |
| #141 | Nemotron 3 Super none | NVIDIA | 1 | 5.5 | 1/3 | 2.36s |
| #143 | MiMo-V2.5 none | Xiaomi | 1 | 5.4 | 1/3 | 2.13s |
| #144 | GPT-5.4 Mini none | OpenAI | 1 | 5.4 | 1/3 | 836ms |
| #146 | Laguna Xs.2 none | Poolside | 1 | 5.3 | 1/3 | 650ms |
| #148 | GPT-5.4 Nano none | OpenAI | 1 | 5.4 | 1/3 | 1.25s |
| #153 | Qwen3.6 35B A3B none | Qwen | 1 | 3.2 | 0/3 | 1.07s |