Kushindwa kwa AI BENCHY
Kushindwa kwa Muda umeisha
Ona ni modeli gani za AI hukutana na Muda umeisha mara nyingi zaidi ili utambue hatari za utegemevu kabla ya kuchagua. Panga kwa: Idadi ya kushindwa ↑.
Kategoria zinazohusiana
| Nafasi | Modeli | Kampuni | Idadi ya Muda umeisha | Wastani wa alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #7 | Qwen3.5-27B medium | Qwen | 1 | 8.2 | 12/16 | 52.1s |
| #10 | Qwen3.5-122B-A10B medium | Qwen | 1 | 7.7 | 12/16 | 29.7s |
| #11 | Claude Sonnet 4.6 medium | Anthropic | 1 | 7.7 | 12/16 | 11.2s |
| #14 | GLM 5 medium | Z.ai | 1 | 7.4 | 11/16 | 16.2s |
| #18 | DeepSeek V3.2 medium | DeepSeek | 1 | 7.3 | 11/16 | 39.5s |
| #27 | GPT-5.2 medium | OpenAI | 1 | 6.5 | 10/16 | 15.3s |
| #28 | Kimi K2.5 medium | Moonshot AI | 1 | 6.4 | 9/16 | 69.8s |
| #30 | Grok 4.1 Fast medium | X AI | 1 | 6.2 | 9/16 | 26.3s |
| #32 | GPT-5 Mini medium | OpenAI | 1 | 6.0 | 8/16 | 25.1s |
| #34 | GPT-5 Nano medium | OpenAI | 1 | 5.5 | 7/16 | 47.9s |
| #4 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 2 | 8.3 | 13/16 | 34.5s |
| #43 | MiniMax M2.5 medium | Minimax | 2 | 4.7 | 5/16 | 43.0s |
| #24 | Qwen3.5-Flash medium | Qwen | 3 | 6.9 | 10/16 | 70.8s |
| #23 | Seed-2.0-Mini medium | Bytedance Seed | 4 | 6.9 | 10/16 | 65.1s |
| #35 | Qwen3.5-35B-A3B medium | Qwen | 4 | 5.5 | 8/16 | 43.9s |