MMMT Bench
Resultados de benchmarks de IA e desempenho dos modelos
Tipo: percentage
Resultados registrados
34
Pontuação média
17.50%
Faixa de pontuação
6% - 84.90%
Modelo líder
84.90% - Ministral 3.0 14B
Pontuações ao longo do tempo
Pontuações individuais do benchmark exibidas por data.
Resultados de modelos
| Organização | Modelos | Data informada | Maior pontuação | Informações | Declarado pelo provedor | Fonte |
|---|---|---|---|---|---|---|
| Ministral 3.0 14B | 02 de dez. de 2025 | 84,90% | Multimodal | Sim | Fonte | |
| Ministral 3.0 8B | 02 de dez. de 2025 | 80,80% | Multimodal | Sim | Fonte | |
| Ministral 3.0 3B | 02 de dez. de 2025 | 78,30% | Multimodal | Sim | Fonte | |
| Pixtral Large | 18 de nov. de 2024 | 74% | - | Sim | Fonte | |
| Pixtral 12B | 17 de set. de 2024 | 60,50% | inferred version-family alias from pixtral-12b-2409 | Sim | Fonte | |
| Qwen 3 VL 235B A22B Instruct | - | 8,50% | - | Sim | - | |
| Qwen 3 VL 235B A22B Thinking | - | 8,50% | - | Sim | - | |
| Qwen 3 VL 32B Instruct | - | 8,40% | - | Sim | - | |
| Qwen 3 VL 32B Thinking | - | 8,30% | - | Sim | - | |
| Qwen 3 VL 30B A3B Instruct | - | 8,10% | - | Sim | - | |
| Qwen 3 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Sim | - | |
| Qwen 3 Guard Stream 8B | - | 8% | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Sim | - | |
| Qwen 3 VL 8B Thinking | - | 8% | - | Sim | - | |
| Qwen 3 VL Embedding 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Sim | - | |
| Qwen 3 VL Reranker 8B | - | 8% | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Sim | - | |
| Qwen 3 VL 30B A3B Thinking | - | 7,90% | - | Sim | - | |
| Qwen 3 4B Instruct 2507 | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sim | - | |
| Qwen 3 4B SafeRL | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sim | - | |
| Qwen 3 4B Thinking 2507 | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sim | - | |
| Qwen 3 Embedding 4B | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sim | - | |
| Qwen 3 Guard Gen 4B | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Sim | - | |
| Qwen 3 Guard Stream 4B | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Sim | - | |
| Qwen 3 Reranker 4B | - | 7,70% | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sim | - | |
| Qwen 3 VL 4B Thinking | - | 7,70% | - | Sim | - | |
| Qwen 3 VL 8B Instruct | - | 7,70% | - | Sim | - |
