TextVQA
Résultats des évaluations de l’IA et performances des modèles
Type: percentageImage To Text
Résultats enregistrés
21
Score moyen
81.95%
Plage des scores
72% - 85.50%
Modèle en tête
85.50% - Qwen 2 VL 2B
Scores au fil du temps
Scores individuels du benchmark tracés par date.
Résultats des modèles
| Organisation | Modèles | Date du résultat | Meilleur score | Informations | Déclaré par le fournisseur | Source |
|---|---|---|---|---|---|---|
| Qwen 2 VL 2B | - | 85,50 % | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Oui | Source | |
| Qwen 2 VL 72B | - | 85,50 % | - | Oui | Source | |
| Qwen 2.5 0.5B | - | 84,90 % | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Oui | Source | |
| Qwen 2.5 1.5B | - | 84,90 % | inferred family alias from qwen2.5-vl-7b (score=0.3131; benches=32) | Oui | Source | |
| Qwen 2.5 3B | - | 84,90 % | inferred family alias from qwen2.5-vl-7b (score=0.3531; benches=32) | Oui | Source | |
| Qwen 2.5 VL 7B Instruct | - | 84,90 % | - | Oui | Source | |
| Qwen 2.5 Coder 3B | - | 84,40 % | inferred family alias from qwen2.5-omni-7b (score=0.3000; benches=45) | Oui | Source | |
| Qwen 2.5 Coder 7B | - | 84,40 % | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4700; benches=45) | Oui | Source | |
| Qwen 2.5 Math 7B | - | 84,40 % | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4767; benches=45) | Oui | Source | |
| Qwen 2.5 Math 7B PRM800K | - | 84,40 % | inferred family alias from qwen2.5-omni-7b (score=0.3696; benches=45) | Oui | Source | |
| Qwen 2.5 Math PRM 7B | - | 84,40 % | inferred family alias from qwen2.5-omni-7b (score=0.4092; benches=45) | Oui | Source | |
| Qwen 2.5 Omni 3B | - | 84,40 % | inferred high-confidence family alias from qwen2.5-omni-7b (score=0.4933; benches=45) | Oui | Source | |
| Qwen 2.5 Omni 7B | - | 84,40 % | - | Oui | Source | |
| DeepSeek VL2 | 13 déc. 2024 | 84,20 % | - | Oui | Source | |
| DeepSeek VL2 Small | 13 déc. 2024 | 83,40 % | - | Oui | Source | |
| DeepSeek VL2 Tiny | 13 déc. 2024 | 80,70 % | - | Oui | Source | |
| Grok 1.5V | 12 avr. 2024 | 78,10 % | - | Oui | Source | |
| Phi 4 multimodal instruct | 01 févr. 2025 | 75,60 % | - | Oui | Source | |
| Llama 3.2 90B Vision Instruct | - | 73,50 % | inferred high-confidence family alias from llama-3.2-90b-instruct (score=0.5873; benches=13) | Oui | Source | |
| Phi 3 Vision 128K Instruct | - | 72 % | inferred family alias from phi-3.5-vision-instruct (score=0.3495; benches=9) | Oui | Source | |
| Phi 3.5 vision instruct | 23 août 2024 | 72 % | - | Oui | Source |
