Kushindwa kwa AI BENCHY
Kushindwa kwa Muundo wa ziada
Ona ni modeli gani za AI hukutana na Muundo wa ziada mara nyingi zaidi ili utambue hatari za utegemevu kabla ya kuchagua. Panga kwa: Idadi ya kushindwa ↑.
| Nafasi | Modeli | Kampuni | Idadi ya Muundo wa ziada | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #10 | Qwen3.5-27B medium | Qwen | 1 | 8.4 | 13/18 | 53.0s |
| #23 | MiMo-V2-Pro medium | Xiaomi | 1 | 8.1 | 12/18 | 12.3s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 1 | 7.7 | 11/18 | 16.8s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 1 | 7.5 | 11/18 | 23.4s |
| #47 | Grok 4.20 medium | X AI | 1 | 7.0 | 9/18 | 10.3s |
| #50 | Hunter Alpha medium | OpenRouter | 1 | 6.7 | 8/18 | 10.3s |
| #82 | Grok 4.20 none | X AI | 1 | 5.2 | 5/18 | 1.11s |
| #87 | Qwen3 Coder Next none | Qwen | 1 | 5.1 | 4/18 | 10.2s |
| #94 | MiMo-V2-Flash none | Xiaomi | 1 | 4.5 | 3/18 | 2.79s |
| #97 | Qwen3.5-9B medium | Qwen | 1 | 4.4 | 3/18 | 73.6s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 2 | 8.0 | 13/18 | 12.7s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 2 | 6.4 | 7/18 | 9.80s |
| #64 | DeepSeek V3.2 none | DeepSeek | 2 | 6.1 | 7/18 | 12.1s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 3 | 7.4 | 11/18 | 4.98s |
| #37 | Claude Opus 4.6 medium | Anthropic | 4 | 7.6 | 12/18 | 21.1s |