Catégorie AI BENCHY
Classement Astuces anti-IA
Voyez quels modèles d'IA réussissent le mieux sur Astuces anti-IA, lesquels restent fiables et où les écarts sont les plus marqués. Trier par: Temps de réponse (moy.) ↓.
| Rang | Modèle | Entreprise | Score Astuces anti-IA | Score | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|
| #72 | DeepSeek V3.2 medium | DeepSeek | 8.2 | 7.0 | 3/4 | 24.2s |
| #17 | GLM 5 medium | Z.ai | 10.0 | 8.3 | 4/4 | 23.7s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.5 | 4/4 | 22.1s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.1 | 4/4 | 21.1s |
| #129 | MiniMax M2.5 medium | Minimax | 7.9 | 5.3 | 2/4 | 20.8s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 3.0 | 5.0 | 0/4 | 20.2s |
| #30 | Qwen3.5-27B medium | Qwen | 8.7 | 7.8 | 3/4 | 19.8s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 8.3 | 8.2 | 3/4 | 18.0s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 6.4 | 6.0 | 2/4 | 16.5s |
| #64 | MiMo-V2-Flash medium | Xiaomi | 8.1 | 7.2 | 3/4 | 15.8s |
| #82 | Hy3 preview high | Tencent | 6.4 | 6.6 | 2/4 | 15.1s |
| #35 | Gemini 3 PRO Preview medium | 10.0 | 7.6 | 4/4 | 15.0s | |
| #158 | GLM 4.7 Flash medium | Z.ai | 4.7 | 4.4 | 1/4 | 15.0s |
| #67 | MiniMax M3 medium | Minimax | 5.5 | 7.1 | 1/4 | 14.9s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 3.5 | 5.7 | 0/4 | 14.0s |