Utatuzi wa mafumbo: Hakufuata maelekezo
Utatuzi wa mafumbo
Hakufuata maelekezo
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Hakufuata maelekezo katika Utatuzi wa mafumbo, ili uone udhaifu haraka.
Sababu za kushindwa
157/157
Chuja miundo
Hakuna miundo inayolingana na utafutaji na vichujio vya sasa.
| Nafasi | Modeli | Kampuni | Idadi ya Hakufuata maelekezo | Alama ya kategoria | Jumla ya gharama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|
| #248 | MiMo-V2.5-Pro medium | Xiaomi | 1 | 0.7 | $0.332 | 1/3 | 5.31s |
| #250 | Dots 3 Note Preview low | Dots Studio | 1 | 0.5 | $0.000 | 1/3 | 8.52s |
| #253 | Qwen3.6 27B none | Qwen | 1 | 0.5 | $0.148 | 1/3 | 5.15s |
| #256 | Minimax M3.1 Flash medium | Minimax | 1 | 0.8 | $0.000 | 2/3 | 4.18s |
| #258 | Solar Pro 4 high | Upstage | 1 | 0.9 | $0.077 | 2/3 | 55.2s |
| #260 | Ling 3.1 Flash low | Inclusionai | 1 | 0.9 | $0.000 | 2/3 | 32.8s |
| #262 | Space Bunny Alpha medium | Stealth | 1 | 0.8 | $0.000 | 2/3 | 3.42s |
| #263 | DeepSeek V3.2 medium | DeepSeek | 1 | 0.7 | $0.152 | 1/3 | 37.7s |
| #264 | Trinity Large Thinking low | Arcee AI | 1 | 0.6 | $0.918 | 1/3 | 3.28s |
| #265 | DeepSeek V4 Flash 0423 none | DeepSeek | 1 | 0.3 | $0.149 | 0/3 | 23.7s |
| #269 | GLM 5 Turbo medium | Z.ai | 1 | 0.9 | $0.323 | 2/3 | 5.23s |
| #272 | Claude Fable 5.1 low | Anthropic | 1 | 0.8 | $3.395 | 2/3 | 4.78s |
| #286 | Inkling Small medium | Thinkingmachines | 1 | 0.6 | $0.113 | 1/3 | 5.24s |
| #289 | gpt-oss-120b medium | OpenAI | 1 | 0.5 | $0.030 | 1/3 | 21.7s |
| #290 | Gemini 3.1 Flash Lite none | 1 | 0.6 | $0.069 | 1/3 | 720ms |