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) |
|---|---|---|---|---|---|---|---|
| #71 | Qwen3.7 Flash high | Qwen | 1 | 8.2 | $0.052 | 2/3 | 58.8s |
| #73 | Seed-2.0-Code low | Bytedance Seed | 1 | 7.0 | $0.767 | 1/3 | 109.7s |
| #76 | DeepSeek V4 Flash 0423 high | DeepSeek | 1 | 7.8 | $0.042 | 2/3 | 50.6s |
| #79 | Solar Pro 4 xhigh | Upstage | 1 | 5.8 | $0.050 | 1/3 | 292.2s |
| #80 | Nemotron 3 Ultra medium | NVIDIA | 1 | 8.4 | $0.780 | 2/3 | 26.5s |
| #81 | Claude Opus 5 none | Anthropic | 1 | 5.9 | $1.550 | 1/3 | 5.54s |
| #86 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 6.6 | $0.459 | 1/3 | 180.7s |
| #88 | GPT-5.4 Mini medium | OpenAI | 1 | 8.4 | $0.786 | 2/3 | 57.9s |
| #89 | Grok Build 0.1 medium | X AI | 1 | 5.7 | $1.130 | 1/3 | 108.5s |
| #98 | Claude Sonnet 4.6 none | Anthropic | 1 | 5.5 | $0.661 | 1/3 | 5.19s |
| #100 | KAT-Coder-Pro V2.5 low | Kwaipilot | 1 | 7.8 | $0.400 | 2/3 | 24.9s |
| #104 | Claude Opus 4.8 none | Anthropic | 1 | 5.5 | $1.166 | 1/3 | 3.29s |
| #107 | Muse Glimmer 30B high | Meta | 1 | 8.8 | $0.535 | 2/3 | 96.0s |
| #110 | Muse Glimmer 30B medium | Meta | 1 | 8.4 | $0.280 | 2/3 | 33.7s |
| #111 | Qwen3.5-122B-A10B medium | Qwen | 1 | 6.0 | $1.047 | 1/3 | 114.5s |