Clasament Respectarea instrucțiunilor
Vezi ce modele AI se descurcă cel mai bine la Respectarea instrucțiunilor, care rămân fiabile și unde apar cele mai mari diferențe.
Modele afișate
15
Media pentru Scor Respectarea instrucțiunilor
8.5
Cel mai bun model
Gemini 3 Flash Preview 10.0
210/210
Filtrează modelele
Niciun model nu corespunde căutării și filtrelor curente.
| Rang | Model | Companie | Scor Respectarea instrucțiunilor | Scor | Cost total | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|---|
| #82 | DeepSeek V4 Pro none | DeepSeek | 6.3 | 6.9 | $0.096 | 1/2 | 4.12s |
| #71 | Qwen3.7 Plus none | Qwen | 6.3 | 7.2 | $0.106 | 1/2 | 929ms |
| #103 | Qwen3.5-27B none | Qwen | 6.3 | 6.5 | $0.090 | 1/2 | 1.03s |
| #124 | Qwen3.6 Flash none | Qwen | 6.3 | 6.1 | $0.062 | 1/2 | 1.10s |
| #125 | Qwen3.5-Flash none | Qwen | 6.3 | 6.1 | $0.073 | 1/2 | 8.81s |
| #127 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 6.1 | $0.106 | 1/2 | 809ms |
| #136 | GPT-5.4 Mini none | OpenAI | 6.3 | 5.9 | $0.095 | 1/2 | 728ms |
| #142 | Qwen3.5-122B-A10B none | Qwen | 6.3 | 5.7 | $0.247 | 1/2 | 513ms |
| #156 | Gemma 4 26B A4B none | 6.3 | 5.5 | $0.015 | 1/2 | 690ms | |
| #164 | Inkling none | Thinkingmachines | 6.3 | 5.2 | $0.147 | 1/2 | 1.72s |
| #166 | Qwen3 Coder Next none | Qwen | 6.3 | 5.1 | $0.025 | 1/2 | 7.78s |
| #174 | GPT-4o-mini none | OpenAI | 6.3 | 5.0 | $0.010 | 1/2 | 1.11s |
| #177 | Nemotron 3 Super none | NVIDIA | 6.3 | 4.9 | $0.008 | 1/2 | 804ms |
| #180 | GPT-5.4 Nano none | OpenAI | 6.3 | 4.8 | $0.041 | 1/2 | 784ms |
| #187 | Qwen3 Coder Next medium | Qwen | 6.3 | 4.7 | $0.032 | 1/2 | 7.49s |