Classement Appel d'outils
Voyez quels modèles d'IA réussissent le mieux sur Appel d'outils, lesquels restent fiables et où les écarts sont les plus marqués.
226/226
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Score Appel d'outils | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #161 | KAT-Coder-Air V2.5 medium | Kwaipilot | 10.0 | 5.6 | $0.048 | 1/1 | 4.77s |
| #162 | DeepSeek V4 Flash none | DeepSeek | 10.0 | 5.6 | $0.042 | 1/1 | 77.9s |
| #163 | GLM 5.1 none | Z.ai | 10.0 | 5.5 | $0.164 | 1/1 | 10.7s |
| #166 | MiMo-V2.5-Pro none | Xiaomi | 10.0 | 5.5 | $0.068 | 1/1 | 3.30s |
| #167 | Kimi K2.5 none | Moonshot AI | 10.0 | 5.5 | $0.127 | 1/1 | 14.0s |
| #168 | Gemma 4 26B A4B none | 10.0 | 5.5 | $0.022 | 1/1 | 57.1s | |
| #169 | Mimo V2 Omni none | Xiaomi | 10.0 | 5.5 | $0.021 | 1/1 | 5.40s |
| #170 | Laguna S 2.1 medium | Poolside | 10.0 | 5.4 | $0.059 | 1/1 | 2.24s |
| #171 | KAT-Coder-Air V2.5 low | Kwaipilot | 10.0 | 5.4 | $0.041 | 1/1 | 4.47s |
| #172 | GPT-5.6 Luna none | OpenAI | 10.0 | 5.4 | $0.142 | 1/1 | 2.80s |
| #173 | Laguna S 2.1 high | Poolside | 10.0 | 5.4 | $0.127 | 1/1 | 2.69s |
| #174 | Laguna XS 2.1 none | Poolside | 10.0 | 5.3 | $0.008 | 1/1 | 1.36s |
| #177 | Gemini 3.1 Flash Lite Preview high | 10.0 | 5.3 | $2.310 | 1/1 | 7.73s | |
| #179 | Mistral Small 4 none | Mistral | 10.0 | 5.1 | $0.022 | 1/1 | 1.40s |
| #180 | Qwen3 Coder Next none | Qwen | 10.0 | 5.1 | $0.025 | 1/1 | 2.47s |