Programare: Răspuns greșit
Programare
Răspuns greșit
Vezi ce modele AI au cele mai mari șanse să întâmpine Răspuns greșit la Programare, ca să găsești mai repede punctele slabe.
Motive de eșec
197/197
Filtrează modelele
Niciun model nu corespunde căutării și filtrelor curente.
| Rang | Model | Companie | Număr de Răspuns greșit | Scor de categorie | Cost total | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|---|
| #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 |