AI BENCHY अपयशे
चुकीचे उत्तर अपयशे
कोणत्या AI मॉडेल्सना चुकीचे उत्तर सर्वाधिक वेळा येतो ते पाहा, म्हणजे निवडण्यापूर्वी विश्वासार्हतेचे धोके लक्षात येतील. क्रम लावा: बरोबर चाचण्या ↑.
| क्रमांक | मॉडेल | कंपनी | चुकीचे उत्तर संख्या | स्कोअर | बरोबर चाचण्या | प्रतिसाद वेळ (सरासरी) |
|---|---|---|---|---|---|---|
| #123 | MiMo-V2.5-Pro none | Xiaomi | 11 | 5.5 | 6/21 | 1.78s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 13 | 5.3 | 6/21 | 3.41s |
| #133 | DeepSeek V3.2 none | DeepSeek | 7 | 5.2 | 6/21 | 13.8s |
| #134 | GLM 5 Turbo none | Z.ai | 13 | 5.2 | 6/21 | 2.82s |
| #135 | Kimi K2.5 none | Moonshot AI | 15 | 5.2 | 6/21 | 13.2s |
| #136 | Elephant Alpha medium | Openrouter | 9 | 5.1 | 6/21 | 1.27s |
| #138 | Ling-2.6-flash none | Inclusionai | 9 | 5.0 | 6/21 | 9.34s |
| #107 | Laguna Xs.2 medium | Poolside | 6 | 5.8 | 6/19 | 6.73s |
| #126 | gpt-oss-120b none | OpenAI | 8 | 5.4 | 6/19 | 21.6s |
| #106 | Grok 4.20 Beta none | X AI | 10 | 5.8 | 6/18 | 1.19s |
| #112 | GLM 5.1 none | Z.ai | 13 | 5.7 | 7/21 | 4.10s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 10 | 5.7 | 7/21 | 12.4s |
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 12 | 5.7 | 7/21 | 4.39s |
| #115 | Qwen3.5-27B none | Qwen | 12 | 5.7 | 7/21 | 1.68s |
| #116 | Hunter Alpha none | OpenRouter | 9 | 5.7 | 6/18 | 4.70s |