Eșecuri AI BENCHY
Eșecuri Timp expirat
Vezi ce modele AI se lovesc cel mai des de Timp expirat, ca să identifici riscurile de fiabilitate înainte să alegi. Sortează după: Număr de eșecuri ↑.
| Rang | Model | Companie | Număr de Timp expirat | Scor | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|
| #11 | Claude Opus 4.7 medium | Anthropic | 1 | 8.7 | 17/21 | 4.73s |
| #17 | GLM 5 medium | Z.ai | 1 | 8.3 | 15/21 | 33.5s |
| #18 | Qwen3.7 Plus medium | Qwen | 1 | 8.2 | 15/21 | 38.9s |
| #23 | GLM 5 Turbo medium | Z.ai | 1 | 8.0 | 14/21 | 23.0s |
| #30 | Qwen3.5-27B medium | Qwen | 1 | 7.8 | 13/21 | 68.4s |
| #42 | GPT-5.2 medium | OpenAI | 1 | 7.5 | 13/21 | 16.9s |
| #51 | Mimo V2 PRO medium | Xiaomi | 1 | 7.4 | 12/21 | 22.2s |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 1 | 7.4 | 13/21 | 17.1s |
| #54 | GPT-5 Mini medium | OpenAI | 1 | 7.3 | 12/21 | 23.6s |
| #62 | Step 3.5 Flash medium | Stepfun | 1 | 7.2 | 11/20 | 72.5s |
| #64 | MiMo-V2-Flash medium | Xiaomi | 1 | 7.2 | 12/21 | 20.1s |
| #86 | Grok 4.1 Fast medium | X AI | 1 | 6.5 | 9/19 | 23.8s |
| #94 | GPT-5 Nano medium | OpenAI | 1 | 6.3 | 9/21 | 42.5s |
| #102 | Gemma 4 26B A4B none | 1 | 6.0 | 8/21 | 5.91s | |
| #105 | Nemotron 3 Super medium | NVIDIA | 1 | 5.8 | 8/21 | 32.0s |