AI BENCHY अपयशे
API त्रुटी अपयशे
कोणत्या AI मॉडेल्सना API त्रुटी सर्वाधिक वेळा येतो ते पाहा, म्हणजे निवडण्यापूर्वी विश्वासार्हतेचे धोके लक्षात येतील.
| क्रमांक | मॉडेल | कंपनी | API त्रुटी संख्या | स्कोअर | बरोबर चाचण्या | प्रतिसाद वेळ (सरासरी) |
|---|---|---|---|---|---|---|
| #143 | LFM2-24B-A2B none | Liquid | 4 | 4.2 | 2/16 | 811ms |
| #121 | gpt-oss-120b none | OpenAI | 3 | 5.2 | 5/19 | 21.9s |
| #14 | Gemma 4 31B medium | 2 | 8.2 | 14/19 | 28.7s | |
| #66 | Gemma 4 31B none | 2 | 6.9 | 10/19 | 3.86s | |
| #76 | Grok 4.20 Multi Agent Beta medium | X AI | 2 | 6.6 | 8/18 | 9.80s |
| #109 | Mistral Small 4 medium | Mistral | 2 | 5.5 | 5/19 | 5.65s |
| #135 | Hy3 preview none | Tencent | 2 | 4.6 | 4/19 | 13.0s |
| #10 | Gemini 3 PRO Preview medium | 1 | 8.4 | 15/19 | 9.06s | |
| #22 | Hy3 preview high | Tencent | 1 | 8.0 | 15/19 | 56.8s |
| #28 | Qwen3.6 Plus medium | Qwen | 1 | 7.9 | 13/19 | 17.1s |
| #34 | Hy3 preview medium | Tencent | 1 | 7.8 | 13/19 | 16.0s |
| #36 | Step 3.5 Flash none | Stepfun | 1 | 7.8 | 9/12 | 39.0s |
| #39 | Hy3 preview low | Tencent | 1 | 7.7 | 14/19 | 24.6s |
| #45 | Qwen3.5-Flash medium | Qwen | 1 | 7.6 | 11/19 | 65.8s |
| #47 | GLM 5.1 medium | Z.ai | 1 | 7.6 | 12/19 | 24.4s |