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: Coût total ↓.
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.) |
|---|---|---|---|---|---|---|---|
| #100 | Qwen3.5-27B medium | Qwen | 1 | 7.5 | $0.982 | 13/22 | 113.3s |
| #60 | Claude Sonnet 5 medium | Anthropic | 1 | 8.2 | $0.922 | 15/22 | 12.5s |
| #70 | GPT-5.6 Terra high | OpenAI | 1 | 8.0 | $0.836 | 14/22 | 11.2s |
| #137 | Grok 4.20 medium | X AI | 1 | 7.0 | $0.805 | 11/22 | 32.6s |
| #102 | GPT-5.4 Mini medium | OpenAI | 1 | 7.5 | $0.786 | 12/22 | 26.7s |
| #28 | Qwen3.8 Max medium | Qwen | 1 | 9.0 | $0.771 | 17/22 | 23.3s |
| #194 | Trinity Large Thinking medium | Arcee AI | 2 | 6.1 | $0.756 | 8/22 | 85.4s |
| #145 | Qwen3.6 Flash medium | Qwen | 1 | 6.8 | $0.741 | 12/22 | 45.0s |
| #93 | Nemotron 3 Ultra medium | NVIDIA | 1 | 7.6 | $0.701 | 13/22 | 33.6s |
| #59 | Muse Spark 1.3 low | Meta | 1 | 8.2 | $0.689 | 15/22 | 16.0s |
| #188 | Qwen3.5-35B-A3B medium | Qwen | 1 | 6.1 | $0.675 | 11/22 | 110.8s |
| #56 | Muse Spark 1.1 low | Meta | 1 | 8.3 | $0.673 | 13/22 | 11.9s |
| #167 | Qwen3.6 35B A3B medium | Qwen | 1 | 6.6 | $0.672 | 12/22 | 58.5s |
| #22 | Gemini 3.8 Flash medium | 1 | 9.1 | $0.653 | 19/22 | 14.5s | |
| #164 | Gemini 3.1 Flash Lite Preview low | 1 | 6.6 | $0.646 | 14/22 | 16.7s |