MMMT Bench
AI बेंचमार्क के परिणाम और मॉडल का प्रदर्शन
प्रकार: percentage
दर्ज परिणाम
34
औसत स्कोर
17.50%
स्कोर सीमा
6% - 84.90%
अग्रणी मॉडल
84.90% - Ministral 3.0 14B
समय के साथ स्कोर
तारीख के अनुसार दिखाए गए अलग-अलग बेंचमार्क स्कोर।
मॉडल परिणाम
| संगठन | मॉडल | रिपोर्ट किया गया | सबसे ऊँचा स्कोर | जानकारी | स्व-रिपोर्ट किया गया | स्रोत |
|---|---|---|---|---|---|---|
| Ministral 3.0 14B | 02 दिस॰ 2025 | 84.90% | Multimodal | हाँ | स्रोत | |
| Ministral 3.0 8B | 02 दिस॰ 2025 | 80.80% | Multimodal | हाँ | स्रोत | |
| Ministral 3.0 3B | 02 दिस॰ 2025 | 78.30% | Multimodal | हाँ | स्रोत | |
| Pixtral Large | 18 नव॰ 2024 | 74% | - | हाँ | स्रोत | |
| Pixtral 12B | 17 सित॰ 2024 | 60.50% | inferred version-family alias from pixtral-12b-2409 | हाँ | स्रोत | |
| Qwen 3 VL 235B A22B Instruct | - | 8.50% | - | हाँ | - | |
| Qwen 3 VL 235B A22B Thinking | - | 8.50% | - | हाँ | - | |
| Qwen 3 VL 32B Instruct | - | 8.40% | - | हाँ | - | |
| Qwen 3 VL 32B Thinking | - | 8.30% | - | हाँ | - | |
| Qwen 3 VL 30B A3B Instruct | - | 8.10% | - | हाँ | - | |
| Qwen 3 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | हाँ | - | |
| Qwen 3 Guard Stream 8B | - | 8% | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | हाँ | - | |
| Qwen 3 VL 8B Thinking | - | 8% | - | हाँ | - | |
| Qwen 3 VL Embedding 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | हाँ | - | |
| Qwen 3 VL Reranker 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | हाँ | - | |
| Qwen 3 VL 30B A3B Thinking | - | 7.90% | - | हाँ | - | |
| Qwen 3 4B Instruct 2507 | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | हाँ | - | |
| Qwen 3 4B SafeRL | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | हाँ | - | |
| Qwen 3 4B Thinking 2507 | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | हाँ | - | |
| Qwen 3 Embedding 4B | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | हाँ | - | |
| Qwen 3 Guard Gen 4B | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | हाँ | - | |
| Qwen 3 Guard Stream 4B | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | हाँ | - | |
| Qwen 3 Reranker 4B | - | 7.70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | हाँ | - | |
| Qwen 3 VL 4B Thinking | - | 7.70% | - | हाँ | - | |
| Qwen 3 VL 8B Instruct | - | 7.70% | - | हाँ | - |