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.
Sababu za kushindwa
197/197
Chuja miundo
Hakuna miundo inayolingana na utafutaji na vichujio vya sasa.
| Nafasi | Modeli | Kampuni | Idadi ya Jibu lisilo sahihi | Alama ya kategoria | Jumla ya gharama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|---|
| #46 | Gemini 2.5 Flash medium | 1 | 7.8 | $0.644 | 2/3 | 41.0s | |
| #47 | Claude Sonnet 5 medium | Anthropic | 1 | 9.0 | $0.922 | 2/3 | 17.3s |
| #51 | Inkling high | Thinkingmachines | 1 | 8.5 | $1.041 | 2/3 | 148.4s |
| #53 | DeepSeek V4 Flash 0731 low | DeepSeek | 1 | 7.3 | $0.072 | 1/3 | 163.3s |
| #56 | Inkling medium | Thinkingmachines | 1 | 8.4 | $0.377 | 2/3 | 25.2s |
| #57 | GPT-5.6 Terra high | OpenAI | 1 | 7.6 | $0.836 | 2/3 | 9.14s |
| #59 | GPT-5.2 Chat none | OpenAI | 1 | 8.8 | $0.594 | 2/3 | 9.82s |
| #60 | Step 3.7 Flash medium | Stepfun | 1 | 8.8 | $0.495 | 2/3 | 27.4s |
| #62 | Qwen3.7 Plus medium | Qwen | 1 | 6.1 | $0.277 | 1/3 | 108.6s |
| #63 | Qwen3.6 Plus medium | Qwen | 1 | 6.1 | $0.418 | 1/3 | 153.1s |
| #64 | Gemini 3.5 Flash Lite medium | 1 | 7.9 | $0.272 | 2/3 | 9.96s | |
| #65 | GLM 5.2 medium | Z.ai | 1 | 8.2 | $0.224 | 2/3 | 41.0s |
| #67 | Claude Sonnet 4.6 medium | Anthropic | 1 | 5.7 | $2.126 | 1/3 | 33.3s |
| #69 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 8.0 | $0.236 | 2/3 | 156.7s |
| #70 | Claude Opus 4.8 low | Anthropic | 1 | 6.6 | $2.089 | 1/3 | 7.58s |