Utatuzi wa mafumbo: Hitilafu ya API
Utatuzi wa mafumbo
Hitilafu ya API
Ona ni modeli gani za AI zina uwezekano mkubwa wa kupata Hitilafu ya API katika Utatuzi wa mafumbo, ili uone udhaifu haraka. Panga kwa: Majaribio sahihi ↓.
Sababu za kushindwa
11/11
Chuja miundo
Hakuna miundo inayolingana na utafutaji na vichujio vya sasa.
| Nafasi | Modeli | Kampuni | Idadi ya Hitilafu ya API | Alama ya kategoria | Jumla ya gharama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|
| #135 | Hy3 preview high | Tencent | 1 | 7.7 | $0.048 | 2/3 | 27.9s |
| #173 | DeepSeek V3.2 none | DeepSeek | 1 | 7.6 | $0.054 | 2/3 | 6.91s |
| #153 | Hy3 preview low | Tencent | 1 | 5.3 | $0.015 | 1/3 | 7.51s |
| #175 | Qwen3.6 Plus Preview medium | Qwen | 2 | 5.3 | $0.000 | 1/3 | 7.52s |
| #186 | Laguna M.1 medium | Poolside | 1 | 5.3 | $0.033 | 1/3 | 10.2s |
| #198 | Laguna Xs.2 medium | Poolside | 1 | 5.3 | $0.015 | 1/3 | 1.93s |
| #205 | Laguna Xs.2 none | Poolside | 1 | 5.3 | $0.004 | 1/3 | 650ms |
| #192 | Laguna M.1 none | Poolside | 1 | 3.0 | $0.009 | 0/3 | 891ms |
| #207 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 2.9 | $0.000 | 0/3 | 1.40s |
| #208 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 1 | 3.0 | $0.000 | 0/3 | 532ms |
| #210 | LFM2-24B-A2B none | Liquid | 1 | 3.8 | $0.001 | 0/3 | 1.78s |