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.) |
|---|---|---|---|---|---|---|---|
| #330 | Hy3 preview medium | Tencent | 1.0 | 0.5 | $0.049 | 4/4 | 6.59s |
| #341 | Mimo V2 PRO medium | Xiaomi | 1.0 | 0.5 | $0.333 | 4/4 | 2.86s |
| #359 | Gemini 3 PRO Preview medium | 1.0 | 0.5 | $0.385 | 4/4 | 15.0s | |
| #364 | Mimo V2 Omni medium | Xiaomi | 1.0 | 0.5 | $0.683 | 4/4 | 2.75s |
| #392 | Gemini 3.1 Flash Lite Preview high | 0.8 | 0.4 | $2.310 | 3/3 | 43.9s | |
| #442 | Step 3.5 Flash none | Stepfun | 1.0 | 0.2 | $0.020 | 4/4 | 35.0s |
| #449 | Tev1 4B Experimental default | Togethercomputer | 0.3 | 1.0 | $0.002 | 1/1 | 602ms |
| #450 | Nimble v3 9B default | Bespoke Labs | 0.3 | 0.8 | ~$0.001 | 1/1 | 73ms |
| #13 | GPT-5.6 Sol low | OpenAI | 0.8 | 1.0 | $1.244 | 3/4 | 2.60s |
| #22 | GPT-5.6 Sol high | OpenAI | 0.9 | 0.9 | $1.595 | 3/4 | 3.39s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 0.8 | 0.9 | $1.645 | 3/4 | 34.8s |
| #30 | Muse Spark Open high | Meta | 0.8 | 0.9 | $1.782 | 3/4 | 253.0s |
| #32 | Muse Wonder medium | Meta | 0.8 | 0.9 | $3.397 | 3/4 | 4.84s |
| #36 | DeepSeek V4.1 Flash 1017 low | DeepSeek | 0.8 | 0.9 | $0.355 | 3/4 | 2.02s |
| #38 | GPT-5.3-Codex medium | OpenAI | 0.9 | 0.9 | $1.318 | 3/4 | 4.16s |