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.) |
|---|---|---|---|---|---|---|---|
| #39 | Claude Fable 5 medium | Anthropic | 1 | 8.6 | $3.004 | 17/22 | 15.0s |
| #56 | Qwen3.8 2.4T A95B low | Qwen | 1 | 8.1 | $2.672 | 15/22 | 119.0s |
| #105 | Qwen3.8 2.4T A95B high | Qwen | 1 | 7.4 | $2.357 | 14/22 | 120.6s |
| #60 | Muse Spark 1.1 high | Meta | 2 | 8.0 | $2.253 | 12/22 | 36.9s |
| #7 | Gemini 3.5 Flash high | 1 | 9.4 | $2.011 | 19/22 | 15.5s | |
| #36 | Muse Spark 1.2 high | Meta | 1 | 8.7 | $1.771 | 14/22 | 26.6s |
| #89 | Claude Opus 5 none | Anthropic | 1 | 7.5 | $1.550 | 12/22 | 7.65s |
| #29 | Muse Spark 1.3 medium | Meta | 1 | 8.8 | $1.469 | 17/22 | 38.6s |
| #38 | Muse Spark 1.1 medium | Meta | 1 | 8.6 | $1.420 | 15/22 | 26.2s |
| #37 | Muse Spark 1.2 medium | Meta | 1 | 8.6 | $1.339 | 14/22 | 19.7s |
| #116 | Kimi K2.6 medium | Moonshot AI | 1 | 7.2 | $1.247 | 12/22 | 115.9s |
| #141 | Step 3.7 Flash high | Stepfun | 1 | 6.8 | $1.229 | 11/22 | 70.1s |
| #122 | Qwen3.5-122B-A10B medium | Qwen | 1 | 7.1 | $1.207 | 14/22 | 65.7s |
| #19 | Qwen3.7 Max medium | Qwen | 1 | 9.1 | $1.157 | 17/22 | 44.3s |
| #183 | Qwen3.5-35B-A3B medium | Qwen | 1 | 6.1 | $1.140 | 11/22 | 110.8s |