Kushindwa kwa AI BENCHY
Kushindwa kwa Jibu lisilo sahihi
Ona ni modeli gani za AI hukutana na Jibu lisilo sahihi mara nyingi zaidi ili utambue hatari za utegemevu kabla ya kuchagua. Panga kwa: Alama ↑.
Kategoria
Katika kategoria Mahususi kwa domeni314 Katika kategoria Mbinu za kupinga AI245 Katika kategoria Uandishi wa msimbo194 Katika kategoria Utatuzi wa mafumbo147 Katika kategoria Maarifa ya jumla130 Katika kategoria Ufuataji wa maagizo53 Katika kategoria Mchanganyiko52 Katika kategoria Uchanganuzi na uchimbaji wa data35 Katika kategoria Akili ya jumla32 Katika kategoria Mwito wa zana2
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 3 | 7.5 | 12/21 | 26.1s |
| #42 | GPT-5.2 medium | OpenAI | 3 | 7.5 | 13/21 | 16.9s |
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 7 | 7.5 | 13/21 | 15.1s |
| #40 | Gemini 3.1 Flash Lite Preview medium | 7 | 7.5 | 13/21 | 3.96s | |
| #39 | Qwen3.6 Flash medium | Qwen | 8 | 7.5 | 12/21 | 19.2s |
| #38 | Grok 4.3 medium | X AI | 5 | 7.6 | 13/21 | 47.5s |
| #37 | Gemma 4 26B A4B medium | 3 | 7.6 | 14/21 | 63.4s | |
| #35 | Gemini 3 PRO Preview medium | 3 | 7.6 | 14/21 | 9.05s | |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 8 | 7.6 | 13/21 | 46.4s |
| #33 | Hy3 preview medium | Tencent | 3 | 7.7 | 14/21 | 16.3s |
| #34 | Qwen3.7 Max none | Qwen | 7 | 7.7 | 14/21 | 1.30s |
| #32 | Gemini 3.5 Flash minimal | 5 | 7.7 | 14/21 | 1.57s | |
| #31 | DeepSeek V4 Flash high | DeepSeek | 6 | 7.7 | 13/21 | 45.8s |
| #30 | Qwen3.5-27B medium | Qwen | 4 | 7.8 | 13/21 | 68.4s |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 5 | 7.8 | 14/21 | 42.5s |