Kushindwa kwa kategoria za AI BENCHY
Uandishi wa msimbo: Jibu lisilo sahihi
Uandishi wa msimbo
Jibu lisilo sahihi
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Jibu lisilo sahihi katika Uandishi wa msimbo, 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) |
|---|---|---|---|---|---|---|
| #32 | MiMo-V2-Omni medium | Xiaomi | 1 | 4.0 | 0/1 | 68.5s |
| #54 | GPT-5 Nano medium | OpenAI | 1 | 6.7 | 0/1 | 40.7s |
| #74 | Trinity Large Preview none | Arcee AI | 1 | 6.3 | 0/1 | 39.5s |
| #69 | Mistral Small 4 medium | Mistral | 1 | 6.7 | 0/1 | 30.5s |
| #65 | gpt-oss-120b medium | OpenAI | 1 | 4.3 | 0/1 | 26.3s |
| #44 | Grok 4.20 medium | X AI | 1 | 4.3 | 0/1 | 24.3s |
| #71 | GLM 5.1 none | Z.ai | 1 | 5.1 | 0/1 | 9.79s |
| #79 | gpt-oss-120b none | OpenAI | 1 | 4.3 | 0/1 | 9.57s |
| #50 | GLM 5 none | Z.ai | 1 | 5.6 | 0/1 | 8.84s |
| #61 | DeepSeek V3.2 none | DeepSeek | 1 | 2.4 | 0/1 | 7.63s |
| #84 | Qwen3.5-9B none | Qwen | 1 | 5.2 | 0/1 | 5.69s |
| #70 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | 0/1 | 5.57s |
| #73 | GLM 5 Turbo none | Z.ai | 1 | 5.3 | 0/1 | 3.93s |
| #46 | Qwen3.5 Plus 2026-02-15 none | Qwen | 1 | 6.3 | 0/1 | 3.63s |
| #66 | Qwen3.5-122B-A10B none | Qwen | 1 | 4.3 | 0/1 | 3.44s |