AI BENCHY श्रेणी
डोमेन-विशिष्ट क्रमवारी
डोमेन-विशिष्ट मध्ये कोणती AI मॉडेल्स सर्वोत्तम काम करतात, कोणती विश्वासार्ह राहतात आणि सर्वात मोठी दरी कुठे दिसते ते पाहा. क्रम लावा: प्रतिसाद वेळ (सरासरी) ↑.
| क्रमांक | मॉडेल | कंपनी | डोमेन-विशिष्ट स्कोअर | स्कोअर | बरोबर चाचण्या | प्रतिसाद वेळ (सरासरी) |
|---|---|---|---|---|---|---|
| #54 | GPT-5 Mini medium | OpenAI | 3.6 | 7.3 | 0/3 | 44.6s |
| #18 | Qwen3.7 Plus medium | Qwen | 3.6 | 8.2 | 0/3 | 45.3s |
| #80 | Mimo V2 Omni medium | Xiaomi | 3.0 | 6.7 | 0/3 | 47.9s |
| #22 | Step 3.7 Flash medium | Stepfun | 7.7 | 8.0 | 2/3 | 48.3s |
| #99 | gpt-oss-120b medium | OpenAI | 2.9 | 6.1 | 0/3 | 50.9s |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 2.9 | 7.6 | 0/3 | 53.1s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 2.9 | 4.6 | 0/3 | 56.7s |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 2.9 | 7.8 | 0/3 | 63.4s |
| #15 | GPT-5.3-Codex medium | OpenAI | 5.9 | 8.4 | 1/3 | 64.3s |
| #75 | Ring-2.6-1T medium | Inclusionai | 3.5 | 6.9 | 0/3 | 64.9s |
| #45 | GPT-5.4 Mini medium | OpenAI | 4.1 | 7.5 | 0/3 | 65.3s |
| #23 | GLM 5 Turbo medium | Z.ai | 2.9 | 8.0 | 0/3 | 71.1s |
| #78 | Qwen3.6 27B medium | Qwen | 2.9 | 6.8 | 0/3 | 73.4s |
| #96 | Ring-2.6-1T none | Inclusionai | 5.3 | 6.2 | 1/3 | 73.4s |
| #21 | GPT-5.4 medium | OpenAI | 5.3 | 8.0 | 1/3 | 74.3s |