Clasament Apelare instrumente
Vezi ce modele AI se descurcă cel mai bine la Apelare instrumente, care rămân fiabile și unde apar cele mai mari diferențe. Sortează după: Cost total ↓.
Modele afișate
15
Media pentru Scor Apelare instrumente
8.8
Cel mai bun model
Grok 4.20 Multi Agent Beta 3.0
316/316
Filtrează modelele
Niciun model nu corespunde căutării și filtrelor curente.
| Rang | Model | Companie | Scor Apelare instrumente | Scor | Cost total | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|---|
| #72 | GPT-5.2 Chat none | OpenAI | 10.0 | 7.9 | $0.594 | 1/1 | 4.68s |
| #277 | Trinity Large Thinking high | Arcee AI | 10.0 | 4.8 | $0.592 | 1/1 | 5.96s |
| #170 | Qwen3.6 27B medium | Qwen | 10.0 | 6.5 | $0.577 | 1/1 | 16.9s |
| #186 | Claude Sonnet 5 none | Anthropic | 10.0 | 6.1 | $0.548 | 1/1 | 6.80s |
| #305 | Grok Build 0.1 none | X AI | 3.0 | 4.0 | $0.547 | 0/1 | 0ms |
| #135 | GPT-5.5 none | OpenAI | 10.0 | 7.0 | $0.544 | 1/1 | 3.90s |
| #35 | Gemini 3.5 Flash Lite high | 10.0 | 8.8 | $0.540 | 1/1 | 4.55s | |
| #98 | GPT 5.3 Chat none | OpenAI | 10.0 | 7.5 | $0.533 | 1/1 | 8.36s |
| #79 | GPT-5.6 Terra medium | OpenAI | 10.0 | 7.8 | $0.523 | 1/1 | 5.09s |
| #13 | GPT-5.6 Sol medium | OpenAI | 10.0 | 9.4 | $0.508 | 1/1 | 6.30s |
| #122 | KAT-Coder-Pro V2.5 high | Kwaipilot | 10.0 | 7.2 | $0.506 | 1/1 | 28.0s |
| #161 | Claude Opus 4.7 none | Anthropic | 10.0 | 6.6 | $0.505 | 1/1 | 4.74s |
| #109 | LongCat 2.0 medium | Meituan | 10.0 | 7.4 | $0.499 | 1/1 | 10.7s |
| #73 | Step 3.7 Flash medium | Stepfun | 10.0 | 7.9 | $0.495 | 1/1 | 4.16s |
| #160 | LongCat 2.0 high | Meituan | 10.0 | 6.7 | $0.492 | 1/1 | 10.0s |