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.
| क्रमांक | मॉडेल | कंपनी | डोमेन-विशिष्ट स्कोअर | स्कोअर | बरोबर चाचण्या | प्रतिसाद वेळ (सरासरी) |
|---|---|---|---|---|---|---|
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.8 | 3/3 | 15.3s | |
| #32 | Gemini 3.5 Flash minimal | 10.0 | 7.7 | 3/3 | 899ms | |
| #83 | Step 3.5 Flash none | Stepfun | 10.0 | 6.6 | 1/1 | 34.5s |
| #3 | Gemini 3.5 Flash low | 7.7 | 9.4 | 2/3 | 3.39s | |
| #4 | Gemini 3.1 Pro Preview medium | 7.7 | 9.4 | 2/3 | 32.7s | |
| #7 | Gemini 3.5 Flash medium | 7.7 | 9.0 | 2/3 | 5.24s | |
| #8 | Claude Opus 4.7 none | Anthropic | 7.7 | 8.9 | 2/3 | 1.19s |
| #11 | Claude Opus 4.7 medium | Anthropic | 7.7 | 8.7 | 2/3 | 1.17s |
| #22 | Step 3.7 Flash medium | Stepfun | 7.7 | 8.0 | 2/3 | 48.3s |
| #27 | Gemma 4 31B medium | 7.7 | 7.8 | 2/3 | 38.5s | |
| #34 | Qwen3.7 Max none | Qwen | 7.7 | 7.7 | 2/3 | 975ms |
| #48 | Gemini 3 Flash Preview none | 7.7 | 7.4 | 2/3 | 963ms | |
| #74 | Qwen3.6 Max Preview none | Qwen | 7.7 | 6.9 | 2/3 | 1.22s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 7.7 | 6.8 | 2/3 | 3.54s |
| #85 | Gemma 4 31B none | 7.7 | 6.5 | 2/3 | 3.22s |