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.) |
|---|---|---|---|---|---|---|---|
| #282 | Granite 4.2 8B high | IBM Granite | 1 | 4.6 | $0.084 | 4/22 | 235.9s |
| #280 | Cobuddy medium | Baidu | 1 | 4.7 | $0.000 | 7/21 | 39.9s |
| #275 | GLM 4.7 Flash none | Z.ai | 2 | 4.8 | $0.016 | 5/22 | 8.81s |
| #272 | Trinity Large Thinking high | Arcee AI | 2 | 4.8 | $0.592 | 5/22 | 75.9s |
| #270 | Nemotron 3.5 Lightning low | NVIDIA | 1 | 4.8 | $0.140 | 5/22 | 59.8s |
| #266 | Ling-2.6-flash none | Inclusionai | 3 | 4.9 | $0.002 | 6/22 | 10.7s |
| #265 | Mercury 2.5 Preview none | Inception | 1 | 4.9 | $0.018 | 4/22 | 3.51s |
| #262 | DeepSeek V3.2 none | DeepSeek | 2 | 5.0 | $0.054 | 6/22 | 17.9s |
| #261 | Laguna S 2.1 low | Poolside | 1 | 5.0 | $0.082 | 3/22 | 85.3s |
| #259 | MiniMax M2.7 medium | Minimax | 1 | 5.0 | $0.208 | 5/22 | 43.2s |
| #258 | North Mini Code none | Cohere | 2 | 5.1 | $0.000 | 4/22 | 29.9s |
| #256 | Qwen3.5-9B none | Qwen | 2 | 5.1 | $0.021 | 4/22 | 19.2s |
| #250 | Nemotron 3.5 Lightning medium | NVIDIA | 1 | 5.1 | $0.156 | 5/22 | 70.1s |
| #248 | Inkling none | Thinkingmachines | 1 | 5.2 | $0.147 | 6/22 | 3.47s |
| #247 | Dots 3 Note Preview none | Dots Studio | 1 | 5.2 | $0.000 | 3/22 | 3.53s |