Kushindwa kwa kategoria za AI BENCHY
Akili ya jumla: Jibu lisilo sahihi
Akili ya jumla
Jibu lisilo sahihi
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Jibu lisilo sahihi katika Akili ya jumla, ili uone udhaifu haraka. Panga kwa: Muda wa majibu (wastani) ↓.
Sababu za kushindwa
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama ya kategoria | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 1 | 4.9 | 0/1 | 25.3s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 1 | 4.2 | 0/1 | 23.7s |
| #47 | Grok Build 0.1 medium | X AI | 1 | 4.4 | 0/1 | 18.4s |
| #158 | GLM 4.7 Flash medium | Z.ai | 1 | 3.6 | 0/1 | 18.1s |
| #96 | Ring-2.6-1T none | Inclusionai | 1 | 4.3 | 0/1 | 15.6s |
| #104 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 1 | 5.0 | 0/1 | 13.5s |
| #100 | Grok Build 0.1 none | X AI | 1 | 4.3 | 0/1 | 12.5s |
| #126 | gpt-oss-120b none | OpenAI | 1 | 4.8 | 0/1 | 10.8s |
| #23 | GLM 5 Turbo medium | Z.ai | 1 | 6.1 | 0/1 | 10.1s |
| #39 | Qwen3.6 Flash medium | Qwen | 1 | 4.8 | 0/1 | 9.88s |
| #57 | Step 3.7 Flash low | Stepfun | 1 | 3.4 | 0/1 | 7.00s |
| #143 | MiMo-V2.5 none | Xiaomi | 1 | 4.4 | 0/1 | 6.86s |
| #22 | Step 3.7 Flash medium | Stepfun | 1 | 4.0 | 0/1 | 6.85s |
| #71 | Step 3.7 Flash high | Stepfun | 1 | 5.5 | 0/1 | 4.17s |
| #80 | Mimo V2 Omni medium | Xiaomi | 1 | 5.4 | 0/1 | 3.61s |