Kushindwa kwa kategoria za AI BENCHY
Mahususi kwa domeni: Jibu lisilo sahihi
Mahususi kwa domeni
Jibu lisilo sahihi
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Jibu lisilo sahihi katika Mahususi kwa domeni, ili uone udhaifu haraka. Panga kwa: Idadi ya kushindwa ↑.
Sababu za kushindwa
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama ya kategoria | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #2 | Gemini 3.1 Pro Preview medium | 1 | 7.7 | 2/3 | 32.7s | |
| #4 | Claude Opus 4.7 none | Anthropic | 1 | 7.7 | 2/3 | 1.19s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 5.3 | 1/3 | 17.5s |
| #10 | Qwen3.5-27B medium | Qwen | 1 | 5.3 | 1/3 | 79.5s |
| #14 | Gemma 4 31B medium | 1 | 7.7 | 2/3 | 38.5s | |
| #21 | Gemini 3 Flash Preview none | 1 | 7.7 | 2/3 | 963ms | |
| #23 | MiMo-V2-Pro medium | Xiaomi | 1 | 5.3 | 1/3 | 6.00s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 1 | 2.9 | 0/3 | 0ms |
| #27 | DeepSeek V3.2 medium | DeepSeek | 1 | 5.3 | 1/3 | 39.3s |
| #32 | Qwen3.5-Flash medium | Qwen | 1 | 5.3 | 1/3 | 146.5s |
| #33 | GLM 5.1 medium | Z.ai | 1 | 5.3 | 1/3 | 29.8s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 1 | 3.0 | 0/3 | 55.1s |
| #37 | Claude Opus 4.6 medium | Anthropic | 1 | 3.0 | 0/3 | 83.4s |
| #40 | GPT-5.2 medium | OpenAI | 1 | 5.9 | 1/3 | 77.8s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.7 | 2/3 | 3.54s |