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: Tests corrects ↑.
451/451
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Score Astuces anti-IA | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #138 | Claude Haiku 5.5 medium | Anthropic | 0.9 | 0.8 | $0.063 | 3/4 | 2.36s |
| #141 | Muse Glimmer 30B medium | Meta | 0.9 | 0.8 | $0.288 | 3/4 | 7.36s |
| #142 | Muse Wonder xhigh | Meta | 0.8 | 0.8 | $4.012 | 3/4 | 6.04s |
| #149 | Mistral Large 4 high | Mistral | 0.8 | 0.8 | $1.391 | 3/4 | 15.0s |
| #150 | Seed-2.0-Code high | Bytedance Seed | 0.8 | 0.7 | $1.448 | 3/4 | 35.1s |
| #151 | GPT-5.6 Luna medium | OpenAI | 0.8 | 0.7 | $0.065 | 3/4 | 2.52s |
| #153 | DeepSeek V4 Flash 0731 low | DeepSeek | 0.8 | 0.7 | $0.306 | 3/4 | 10.1s |
| #155 | GLM 5.3 FlashX high | Z.ai | 0.8 | 0.7 | $0.210 | 3/4 | 1.98s |
| #159 | Inkling medium | Thinkingmachines | 0.9 | 0.7 | $0.527 | 3/4 | 6.49s |
| #161 | GLM 5.3 Flash high | Z.ai | 0.8 | 0.7 | $0.056 | 3/4 | 2.50s |
| #162 | Claude Fable 5.1 medium | Anthropic | 0.8 | 0.7 | $3.197 | 3/4 | 5.18s |
| #164 | Gemini 2.5 Flash medium | 0.8 | 0.7 | $0.680 | 3/4 | 6.30s | |
| #165 | LongCat 2.0 high | Meituan | 0.9 | 0.7 | $0.778 | 3/4 | 7.76s |
| #169 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 0.8 | 0.7 | $0.567 | 3/4 | 45.8s |
| #176 | Step 3.7 Flash low | Stepfun | 0.9 | 0.7 | $0.449 | 3/4 | 4.02s |