Échecs Appel d'outil invalide
Voyez quels modèles d'IA rencontrent le plus souvent Appel d'outil invalide, pour repérer les risques de fiabilité avant de choisir. Trier par: Score ↓.
131/131
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Nombre de Appel d'outil invalide | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #188 | Inkling low | Thinkingmachines | 2 | 6.1 | $0.187 | 10/22 | 5.11s |
| #189 | Trinity Large Thinking medium | Arcee AI | 2 | 6.1 | $0.756 | 8/22 | 85.4s |
| #190 | Qwen3.6 Flash none | Qwen | 2 | 6.1 | $0.062 | 7/22 | 3.73s |
| #194 | Trinity Large Thinking low | Arcee AI | 2 | 6.0 | $0.625 | 8/22 | 96.6s |
| #195 | Gemini 2.5 Flash none | 1 | 6.0 | $0.017 | 8/22 | 6.19s | |
| #197 | GPT-5.6 Terra none | OpenAI | 1 | 6.0 | $0.280 | 8/22 | 1.66s |
| #200 | Qwen3.5-Flash none | Qwen | 1 | 6.0 | $0.073 | 7/22 | 25.3s |
| #201 | Qwen3.5-35B-A3B none | Qwen | 1 | 5.9 | $0.142 | 6/22 | 12.7s |
| #206 | GLM 5.3 Flash low | Z.ai | 1 | 5.9 | $0.015 | 10/22 | 9.65s |
| #211 | North Mini Code medium | Cohere | 1 | 5.7 | $0.000 | 8/22 | 142.0s |
| #214 | Inkling Small low | Thinkingmachines | 2 | 5.7 | $0.055 | 9/22 | 2.07s |
| #215 | Ling-3.0-flash none | Inclusionai | 1 | 5.7 | $0.004 | 6/22 | 3.56s |
| #216 | GLM 5.1 none | Z.ai | 1 | 5.7 | $0.164 | 8/22 | 6.74s |
| #218 | Qwen3.5-122B-A10B none | Qwen | 1 | 5.7 | $0.283 | 6/22 | 12.9s |
| #223 | Gemma 4 26B A4B none | 1 | 5.6 | $0.015 | 9/22 | 7.58s |