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. Trier par: Coût total ↑.
311/311
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.) |
|---|---|---|---|---|---|---|---|
| #240 | Laguna S 2.1 high | Poolside | 10.0 | 5.4 | $0.114 | 1/1 | 2.69s |
| #229 | Qwen3.6 27B none | Qwen | 9.5 | 5.5 | $0.116 | 1/1 | 6.74s |
| #133 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 7.0 | $0.116 | 1/1 | 88.7s |
| #100 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 7.4 | $0.117 | 1/1 | 3.80s | |
| #199 | GPT-5 Nano medium | OpenAI | 10.0 | 6.0 | $0.118 | 1/1 | 33.3s |
| #112 | Gemini 3.1 Flash Lite medium | 10.0 | 7.3 | $0.120 | 1/1 | 4.55s | |
| #192 | Qwen3.5 Plus 2026-04-20 none | Qwen | 10.0 | 6.1 | $0.122 | 1/1 | 4.42s |
| #202 | Step 3.5 Flash medium | Stepfun | 10.0 | 5.9 | $0.132 | 1/1 | 11.9s |
| #227 | Nemotron 3.5 Lightning high | NVIDIA | 10.0 | 5.6 | $0.134 | 1/1 | 6.92s |
| #205 | Hy3 preview high | Tencent | 10.0 | 5.9 | $0.135 | 1/1 | 78.8s |
| #157 | Gemini 3.5 Flash Lite low | 10.0 | 6.6 | $0.138 | 1/1 | 1.39s | |
| #270 | Nemotron 3.5 Lightning low | NVIDIA | 10.0 | 4.8 | $0.140 | 1/1 | 5.08s |
| #187 | Qwen3.5-Flash medium | Qwen | 10.0 | 6.1 | $0.142 | 1/1 | 10.3s |
| #90 | GPT-5.4 Nano medium | OpenAI | 10.0 | 7.5 | $0.142 | 1/1 | 7.71s |
| #201 | Qwen3.5-35B-A3B none | Qwen | 10.0 | 5.9 | $0.142 | 1/1 | 2.30s |