Eșecuri AI BENCHY
Eșecuri Apel de instrument invalid
Vezi ce modele AI se lovesc cel mai des de Apel de instrument invalid, ca să identifici riscurile de fiabilitate înainte să alegi.
| Rang | Model | Companie | Număr de Apel de instrument invalid | Scor | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|
| #31 | GLM 5V Turbo medium | Z.ai | 2 | 7.8 | 11/18 | 15.0s |
| #64 | DeepSeek V3.2 none | DeepSeek | 1 | 6.1 | 7/18 | 12.1s |
| #71 | MiniMax M2.5 medium | Minimax | 1 | 5.7 | 5/18 | 39.6s |
| #74 | GLM 4.7 Flash none | Z.ai | 1 | 5.6 | 5/18 | 3.35s |
| #75 | GLM 5.1 none | Z.ai | 1 | 5.6 | 5/18 | 4.33s |
| #79 | Grok 4.20 Beta none | X AI | 1 | 5.3 | 4/18 | 1.19s |
| #80 | MiniMax M2.7 medium | Minimax | 1 | 5.3 | 4/18 | 31.1s |
| #81 | Elephant medium | Openrouter | 1 | 5.2 | 5/18 | 1.27s |
| #82 | Grok 4.20 none | X AI | 1 | 5.2 | 5/18 | 1.11s |
| #85 | Elephant none | Openrouter | 1 | 5.2 | 5/18 | 1.23s |
| #90 | Qwen3.5-9B none | Qwen | 1 | 4.8 | 4/18 | 1.47s |
| #93 | GLM 4.7 Flash medium | Z.ai | 1 | 4.6 | 4/18 | 32.3s |