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.) |
|---|---|---|---|---|---|---|---|
| #84 | DeepSeek V4 Flash 0423 high | DeepSeek | 1 | 7.6 | $0.039 | 13/22 | 51.8s |
| #79 | Qwen3.7 Flash high | Qwen | 1 | 7.8 | $0.052 | 13/22 | 41.4s |
| #76 | Qwen3.8 27B medium | Qwen | 1 | 7.8 | ~$0.058 | 14/22 | 33.0s |
| #72 | Gemini 3.5 Flash Lite medium | 1 | 7.8 | $0.272 | 14/22 | 5.12s | |
| #70 | Qwen3.7 Plus medium | Qwen | 1 | 7.9 | $0.277 | 15/22 | 53.5s |
| #68 | Step 3.7 Flash medium | Stepfun | 1 | 7.9 | $0.495 | 13/22 | 23.5s |
| #65 | GPT-5.6 Terra high | OpenAI | 1 | 8.0 | $0.836 | 14/22 | 11.2s |
| #64 | Inkling medium | Thinkingmachines | 1 | 8.0 | $0.383 | 15/22 | 15.7s |
| #60 | Muse Spark 1.1 high | Meta | 2 | 8.0 | $2.253 | 12/22 | 36.9s |
| #59 | Inkling high | Thinkingmachines | 2 | 8.0 | $1.046 | 15/22 | 62.6s |
| #58 | Muse Glimmer 30B xhigh | Meta | 1 | 8.1 | $0.510 | 13/22 | 95.6s |
| #56 | Qwen3.8 2.4T A95B low | Qwen | 1 | 8.1 | $2.672 | 15/22 | 119.0s |
| #55 | Claude Sonnet 5 medium | Anthropic | 1 | 8.2 | $0.922 | 15/22 | 12.5s |
| #54 | Muse Spark 1.3 low | Meta | 1 | 8.2 | $0.689 | 15/22 | 16.0s |
| #51 | Muse Spark 1.1 low | Meta | 1 | 8.3 | $0.673 | 13/22 | 11.9s |