InfoVQAtest
Résultats des évaluations de l’IA et performances des modèles
Type: percentageMultimodal
Résultats enregistrés
24
Score moyen
85.08%
Plage des scores
80.30% - 92.60%
Modèle en tête
92.60% - Kimi K2.5
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 |
|---|---|---|---|---|---|---|
| Kimi K2.5 | 27 janv. 2026 | 92,60 % | - | Oui | Source | |
| Qwen 3 VL 235B A22B Thinking | - | 89,50 % | - | Oui | - | |
| Qwen 3 VL 235B A22B Instruct | - | 89,20 % | - | Oui | - | |
| Qwen 3 VL 32B Thinking | - | 89,20 % | - | Oui | - | |
| Qwen 3 VL 32B Instruct | - | 87 % | - | Oui | - | |
| Qwen 3 8B | - | 86 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Oui | - | |
| Qwen 3 Guard Stream 8B | - | 86 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Oui | - | |
| Qwen 3 VL 30B A3B Thinking | - | 86 % | - | Oui | - | |
| Qwen 3 VL 8B Thinking | - | 86 % | - | Oui | - | |
| Qwen 3 VL Embedding 8B | - | 86 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Oui | - | |
| Qwen 3 VL Reranker 8B | - | 86 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Oui | - | |
| Qwen 2 VL 2B | - | 84,50 % | inferred family alias from qwen2-vl-72b (score=0.4083; benches=15) | Oui | Source | |
| Qwen 2 VL 72B | - | 84,50 % | - | Oui | Source | |
| Qwen 3 VL 8B Instruct | - | 83,10 % | - | Oui | - | |
| Qwen 3 4B Instruct 2507 | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Oui | - | |
| Qwen 3 4B SafeRL | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 4B Thinking 2507 | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Oui | - | |
| Qwen 3 Embedding 4B | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 Guard Gen 4B | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Oui | - | |
| Qwen 3 Guard Stream 4B | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Oui | - | |
| Qwen 3 Reranker 4B | - | 83 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 VL 4B Thinking | - | 83 % | - | Oui | - | |
| Qwen 3 VL 30B A3B Instruct | - | 82 % | - | Oui | - | |
| Qwen 3 VL 4B Instruct | - | 80,30 % | - | Oui | - |