TextVQA
Resultados de benchmarks de IA e desempenho dos modelos
Tipo: percentageImage To Text
Resultados registrados
21
Pontuação média
81.95%
Faixa de pontuação
72% - 85.50%
Modelo líder
85.50% - Qwen 2 VL 2B
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 |
|---|---|---|---|---|---|---|
| Qwen 2 VL 2B | - | 85,50% | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Sim | Fonte | |
| Qwen 2 VL 72B | - | 85,50% | - | Sim | Fonte | |
| Qwen 2.5 0.5B | - | 84,90% | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Sim | Fonte | |
| Qwen 2.5 1.5B | - | 84,90% | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Sim | Fonte | |
| Qwen 2.5 3B | - | 84,90% | inferred family alias from qwen2.5-vl-7b (score=0.3531; benches=32) | Sim | Fonte | |
| Qwen 2.5 VL 7B Instruct | - | 84,90% | - | Sim | Fonte | |
| Qwen 2.5 Coder 3B | - | 84,40% | inferred family alias from qwen2.5-omni-7b (score=0.3000; benches=45) | Sim | Fonte | |
| Qwen 2.5 Coder 7B | - | 84,40% | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4700; benches=45) | Sim | Fonte | |
| Qwen 2.5 Math 7B | - | 84,40% | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4767; benches=45) | Sim | Fonte | |
| Qwen 2.5 Math 7B PRM800K | - | 84,40% | inferred family alias from qwen2.5-omni-7b (score=0.3696; benches=45) | Sim | Fonte | |
| Qwen 2.5 Math PRM 7B | - | 84,40% | inferred family alias from qwen2.5-omni-7b (score=0.4092; benches=45) | Sim | Fonte | |
| Qwen 2.5 Omni 3B | - | 84,40% | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4933; benches=45) | Sim | Fonte | |
| Qwen 2.5 Omni 7B | - | 84,40% | - | Sim | Fonte | |
| DeepSeek VL2 | 13 de dez. de 2024 | 84,20% | - | Sim | Fonte | |
| DeepSeek VL2 Small | 13 de dez. de 2024 | 83,40% | - | Sim | Fonte | |
| DeepSeek VL2 Tiny | 13 de dez. de 2024 | 80,70% | - | Sim | Fonte | |
| Grok 1.5V | 12 de abr. de 2024 | 78,10% | - | Sim | Fonte | |
| Phi 4 multimodal instruct | 01 de fev. de 2025 | 75,60% | - | Sim | Fonte | |
| Llama 3.2 90B Vision Instruct | - | 73,50% | inferred high-confidence family alias from llama-3.2-90b-instruct (score=0.5873; benches=13) | Sim | Fonte | |
| Phi 3 Vision 128K Instruct | - | 72% | inferred family alias from phi-3.5-vision-instruct (score=0.3495; benches=9) | Sim | Fonte | |
| Phi 3.5 vision instruct | 23 de ago. de 2024 | 72% | - | Sim | Fonte |
