MMMT Bench
Resultados de evaluaciones comparativas de IA y rendimiento de modelos
Tipo: percentage
Resultados registrados
34
Puntuación media
17.50%
Rango de puntuaciones
6% - 84.90%
Modelo líder
84.90% - Ministral 3.0 14B
Puntuaciones a lo largo del tiempo
Puntuaciones individuales de la evaluación a lo largo del tiempo.
Resultados de modelos
| Organización | Modelos | Fecha del resultado | Mejor puntuación | Información | Autodeclarado | Fuente |
|---|---|---|---|---|---|---|
| Ministral 3.0 14B | 02 dic 2025 | 84,90 % | Multimodal | Sí | Fuente | |
| Ministral 3.0 8B | 02 dic 2025 | 80,80 % | Multimodal | Sí | Fuente | |
| Ministral 3.0 3B | 02 dic 2025 | 78,30 % | Multimodal | Sí | Fuente | |
| Pixtral Large | 18 nov 2024 | 74 % | - | Sí | Fuente | |
| Pixtral 12B | 17 sept 2024 | 60,50 % | inferred version-family alias from pixtral-12b-2409 | Sí | Fuente | |
| Qwen 3 VL 235B A22B Instruct | - | 8,50 % | - | Sí | - | |
| Qwen 3 VL 235B A22B Thinking | - | 8,50 % | - | Sí | - | |
| Qwen 3 VL 32B Instruct | - | 8,40 % | - | Sí | - | |
| Qwen 3 VL 32B Thinking | - | 8,30 % | - | Sí | - | |
| Qwen 3 VL 30B A3B Instruct | - | 8,10 % | - | Sí | - | |
| Qwen 3 8B | - | 8 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Sí | - | |
| Qwen 3 Guard Stream 8B | - | 8 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Sí | - | |
| Qwen 3 VL 8B Thinking | - | 8 % | - | Sí | - | |
| Qwen 3 VL Embedding 8B | - | 8 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Sí | - | |
| Qwen 3 VL Reranker 8B | - | 8 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Sí | - | |
| Qwen 3 VL 30B A3B Thinking | - | 7,90 % | - | Sí | - | |
| Qwen 3 4B Instruct 2507 | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - | |
| Qwen 3 4B SafeRL | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 4B Thinking 2507 | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - | |
| Qwen 3 Embedding 4B | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 Guard Gen 4B | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Sí | - | |
| Qwen 3 Guard Stream 4B | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Sí | - | |
| Qwen 3 Reranker 4B | - | 7,70 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 VL 4B Thinking | - | 7,70 % | - | Sí | - | |
| Qwen 3 VL 8B Instruct | - | 7,70 % | - | Sí | - |