Clasament Sarcini agentice
Vezi ce modele AI se descurcă cel mai bine la Sarcini agentice, care rămân fiabile și unde apar cele mai mari diferențe. Sortează după: Cost total ↑.
Modele afișate
15
Media pentru Scor Sarcini agentice
0.6
Cel mai bun model
Ernie 5.5 Flash Preview 0.6
514/514
Filtrează modelele
Niciun model nu corespunde căutării și filtrelor curente.
| Rang | Model | Companie | Scor Sarcini agentice | Scor | Cost total | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|---|
| #63 | Qwen3.8 Max (0902) medium | Qwen | 1.0 | 0.9 | $1.096 | 1/1 | 127.5s |
| #272 | Claude Sonnet 5.5 medium | Anthropic | 1.0 | 0.7 | $1.100 | 1/1 | 51.2s |
| #158 | GPT-5.4 Mini medium | OpenAI | 1.0 | 0.8 | $1.102 | 1/1 | 100.7s |
| #107 | Qwen3.8 Max (0902) low | Qwen | 0.6 | 0.9 | $1.131 | 0/1 | 136.0s |
| #227 | Qwen3.6 Max Preview medium | Qwen | 0.0 | 0.7 | $1.132 | 0/0 | 0ms |
| #155 | Qwen3.5-27B medium | Qwen | 1.0 | 0.8 | $1.135 | 1/1 | 146.5s |
| #231 | Kimi K2.7 Code medium | Moonshot AI | 0.5 | 0.7 | $1.136 | 0/1 | 104.0s |
| #234 | Qwen3.5-122B-A10B medium | Qwen | 0.6 | 0.7 | $1.152 | 0/1 | 95.3s |
| #104 | Claude Sonnet 5.5 high | Anthropic | 1.0 | 0.9 | $1.175 | 1/1 | 51.5s |
| #45 | Qwen3.8 MAX medium | Qwen | 1.0 | 0.9 | $1.181 | 1/1 | 115.3s |
| #99 | DeepSeek V4.1 Flash max | DeepSeek | 1.0 | 0.9 | $1.204 | 1/1 | 66.6s |
| #264 | GPT-5.5 none | OpenAI | 0.5 | 0.7 | $1.212 | 0/1 | 57.5s |
| #120 | Inkling high | Thinkingmachines | 1.0 | 0.8 | $1.238 | 1/1 | 66.0s |
| #14 | GPT-5.6 Sol low | OpenAI | 1.0 | 1.0 | $1.244 | 1/1 | 57.1s |
| #312 | Grok 4.20 medium | X AI | 0.3 | 0.6 | $1.246 | 0/1 | 128.3s |