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.
83/83
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.) |
|---|---|---|---|---|---|---|---|
| #201 | Granite 4.1 8B none | IBM Granite | 2 | 4.0 | $0.007 | 2/22 | 1.45s |
| #2 | Gemini 3.5 Flash high | 1 | 9.5 | $1.976 | 20/22 | 15.1s | |
| #8 | Qwen3.7 Max medium | Qwen | 1 | 9.2 | $1.116 | 18/22 | 40.6s |
| #11 | Gemini 3.5 Flash low | 1 | 8.9 | $0.433 | 19/22 | 5.55s | |
| #16 | Muse Spark 1.1 medium | Meta | 1 | 8.6 | $1.357 | 15/22 | 25.0s |
| #17 | Claude Fable 5 medium | Anthropic | 1 | 8.6 | $3.478 | 17/22 | 17.2s |
| #23 | Claude Sonnet 5 medium | Anthropic | 1 | 8.3 | $0.922 | 16/22 | 12.5s |
| #24 | Muse Spark 1.1 low | Meta | 1 | 8.3 | $0.647 | 13/22 | 11.5s |
| #29 | Step 3.7 Flash medium | Stepfun | 1 | 8.0 | $0.515 | 14/22 | 26.4s |
| #32 | Inkling medium | Thinkingmachines | 1 | 8.0 | $0.391 | 15/22 | 16.2s |
| #34 | GPT-5.6 Terra high | OpenAI | 1 | 8.0 | $1.055 | 14/22 | 11.3s |
| #36 | Qwen3.7 Plus medium | Qwen | 1 | 7.9 | $0.267 | 15/22 | 51.5s |
| #45 | DeepSeek V4 Flash high | DeepSeek | 1 | 7.7 | $0.042 | 13/22 | 49.7s |
| #51 | Nemotron 3 Ultra medium | NVIDIA | 1 | 7.5 | $0.774 | 13/22 | 32.2s |
| #55 | GPT-5.6 Terra low | OpenAI | 1 | 7.5 | $0.519 | 13/22 | 5.31s |