MathVista-Mini
Resultados de evaluaciones comparativas de IA y rendimiento de modelos
Tipo: percentageMath
Resultados registrados
39
Puntuación media
78.79%
Rango de puntuaciones
68.20% - 90.10%
Modelo líder
90.10% - Kimi K2.5
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 |
|---|---|---|---|---|---|---|
| Kimi K2.5 | 27 ene 2026 | 90,10 % | - | Sí | Fuente | |
| Qwen 3.5 27B | 24 feb 2026 | 87,80 % | - | Sí | Fuente | |
| Qwen 3.5 Flash | 23 feb 2026 | 87,80 % | inferred family alias from qwen3.5-27b (score=0.4147; benches=81) | Sí | Fuente | |
| Qwen 3.5 122B A10B | 24 feb 2026 | 87,40 % | - | Sí | Fuente | |
| Qwen 3.5 35B A3B | 24 feb 2026 | 86,20 % | - | Sí | Fuente | |
| Qwen 3 VL 32B Thinking | - | 85,90 % | - | Sí | - | |
| Qwen 3 VL 235B A22B Thinking | - | 85,80 % | - | Sí | - | |
| Qwen 3 VL 235B A22B Instruct | - | 84,90 % | - | Sí | - | |
| Qwen 3 VL 32B Instruct | - | 83,80 % | - | Sí | - | |
| Qwen 3 VL 30B A3B Thinking | - | 81,90 % | - | Sí | - | |
| Qwen 3 8B | - | 81,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Sí | - | |
| Qwen 3 Guard Stream 8B | - | 81,40 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Sí | - | |
| Qwen 3 VL 8B Thinking | - | 81,40 % | - | Sí | - | |
| Qwen 3 VL Embedding 8B | - | 81,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Sí | - | |
| Qwen 3 VL Reranker 8B | - | 81,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Sí | - | |
| Qwen 3 VL 30B A3B Instruct | - | 80,10 % | - | Sí | - | |
| Qwen 3 4B Instruct 2507 | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - | |
| Qwen 3 4B SafeRL | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 4B Thinking 2507 | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Sí | - | |
| Qwen 3 Embedding 4B | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 Guard Gen 4B | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Sí | - | |
| Qwen 3 Guard Stream 4B | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Sí | - | |
| Qwen 3 Reranker 4B | - | 79,50 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Sí | - | |
| Qwen 3 VL 4B Thinking | - | 79,50 % | - | Sí | - | |
| Qwen 3 VL 8B Instruct | - | 77,20 % | - | Sí | - |