Creative Writing v3
Résultats des évaluations de l’IA et performances des modèles
Type: percentageCreativity
Résultats enregistrés
22
Score moyen
156%
Plage des scores
76.10% - 1722%
Modèle en tête
1722% - Grok 4.1 Thinking
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 |
|---|---|---|---|---|---|---|
| Grok 4.1 Thinking | 17 nov. 2025 | 1 722 % | inferred modality/version alias from grok-4.1-thinking-2025-11-17 | Oui | Source | |
| Qwen 3 VL 235B A22B Instruct | - | 86,50 % | - | Oui | - | |
| Qwen 3 235B A22B Thinking 2507 | - | 86,10 % | - | Oui | Source | |
| Qwen 3 VL 235B A22B Thinking | - | 85,70 % | - | Oui | - | |
| Qwen 3 VL 32B Instruct | - | 85,60 % | - | Oui | - | |
| Qwen 3 Next 80B A3B Instruct | - | 85,30 % | - | Oui | Source | |
| Qwen 3 VL 30B A3B Instruct | - | 84,60 % | - | Oui | - | |
| Qwen 3 VL 32B Thinking | - | 83,30 % | - | Oui | - | |
| Qwen 3 VL 30B A3B Thinking | - | 82,50 % | - | Oui | - | |
| Qwen 3 8B | - | 82,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.4600; benches=50) | Oui | - | |
| Qwen 3 Guard Stream 8B | - | 82,40 % | inferred family alias from qwen3-vl-8b-thinking (score=0.3371; benches=50) | Oui | - | |
| Qwen 3 VL 8B Thinking | - | 82,40 % | - | Oui | - | |
| Qwen 3 VL Embedding 8B | - | 82,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5232; benches=50) | Oui | - | |
| Qwen 3 VL Reranker 8B | - | 82,40 % | inferred high-confidence family alias from qwen3-vl-8b-thinking (score=0.5275; benches=50) | Oui | - | |
| Qwen 3 4B Instruct 2507 | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Oui | - | |
| Qwen 3 4B SafeRL | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 4B Thinking 2507 | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3462; benches=48) | Oui | - | |
| Qwen 3 Embedding 4B | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 Guard Gen 4B | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3400; benches=48) | Oui | - | |
| Qwen 3 Guard Stream 4B | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3371; benches=48) | Oui | - | |
| Qwen 3 Reranker 4B | - | 76,10 % | inferred family alias from qwen3-vl-4b-thinking (score=0.3850; benches=48) | Oui | - | |
| Qwen 3 VL 4B Thinking | - | 76,10 % | - | Oui | - |