AI BENCHY अपयशे
चुकीचे उत्तर अपयशे
कोणत्या AI मॉडेल्सना चुकीचे उत्तर सर्वाधिक वेळा येतो ते पाहा, म्हणजे निवडण्यापूर्वी विश्वासार्हतेचे धोके लक्षात येतील.
| क्रमांक | मॉडेल | कंपनी | चुकीचे उत्तर संख्या | स्कोअर | बरोबर चाचण्या | प्रतिसाद वेळ (सरासरी) |
|---|---|---|---|---|---|---|
| #155 | Mercury 2 none | Inception | 16 | 4.5 | 4/21 | 653ms |
| #135 | Kimi K2.5 none | Moonshot AI | 15 | 5.2 | 6/21 | 13.2s |
| #142 | Mistral Small 4 none | Mistral | 15 | 4.9 | 5/21 | 630ms |
| #147 | GPT-4o-mini none | OpenAI | 15 | 4.8 | 5/21 | 1.77s |
| #148 | GPT-5.4 Nano none | OpenAI | 15 | 4.7 | 4/21 | 1.48s |
| #140 | Qwen3 Coder Next none | Qwen | 14 | 4.9 | 5/21 | 8.62s |
| #141 | Nemotron 3 Super none | NVIDIA | 14 | 4.9 | 5/21 | 5.30s |
| #143 | MiMo-V2.5 none | Xiaomi | 14 | 4.9 | 5/21 | 2.20s |
| #154 | Qwen3.5-9B none | Qwen | 14 | 4.6 | 4/21 | 1.89s |
| #108 | Qwen3.5-Flash none | Qwen | 13 | 5.8 | 8/21 | 3.58s |
| #110 | Seed-2.0-Lite none | Bytedance Seed | 13 | 5.8 | 8/21 | 2.49s |
| #112 | GLM 5.1 none | Z.ai | 13 | 5.7 | 7/21 | 4.10s |
| #122 | GLM 4.7 Flash none | Z.ai | 13 | 5.5 | 6/21 | 2.86s |
| #125 | GPT-5.4 none | OpenAI | 13 | 5.5 | 7/21 | 1.42s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 13 | 5.3 | 6/21 | 3.41s |