Clasament Rezolvare de puzzle-uri
Vezi ce modele AI se descurcă cel mai bine la Rezolvare de puzzle-uri, care rămân fiabile și unde apar cele mai mari diferențe. Sortează după: Cost total ↓.
Modele afișate
15
Media pentru Scor Rezolvare de puzzle-uri
6.9
Cel mai bun model
Grok 4.20 Multi Agent Beta 6.7
316/316
Filtrează modelele
Niciun model nu corespunde căutării și filtrelor curente.
| Rang | Model | Companie | Scor Rezolvare de puzzle-uri | Scor | Cost total | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|---|
| #146 | Step 3.7 Flash high | Stepfun | 5.3 | 6.8 | $1.229 | 1/3 | 10.2s |
| #127 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 7.1 | $1.207 | 3/3 | 17.9s |
| #68 | GLM 5.2 high | Z.ai | 6.0 | 8.0 | $1.188 | 1/3 | 33.7s |
| #52 | GPT-5.2 medium | OpenAI | 7.5 | 8.4 | $1.182 | 2/3 | 5.80s |
| #120 | Claude Opus 4.8 none | Anthropic | 7.7 | 7.3 | $1.166 | 2/3 | 2.74s |
| #24 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | $1.157 | 3/3 | 8.84s |
| #147 | Seed-2.0-Code medium | Bytedance Seed | 8.2 | 6.8 | $1.153 | 2/3 | 34.3s |
| #45 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.6 | $1.132 | 3/3 | 24.3s |
| #103 | Grok Build 0.1 medium | X AI | 7.7 | 7.5 | $1.130 | 2/3 | 18.3s |
| #37 | Claude Opus 5 low | Anthropic | 10.0 | 8.7 | $1.121 | 3/3 | 4.23s |
| #144 | Gemini 3.5 Flash none | 10.0 | 6.9 | $1.093 | 3/3 | 3.13s | |
| #64 | Inkling high | Thinkingmachines | 6.9 | 8.0 | $1.046 | 1/3 | 10.7s |
| #30 | GPT-5.3-Codex medium | OpenAI | 9.0 | 8.9 | $0.988 | 2/3 | 5.05s |
| #100 | Qwen3.5-27B medium | Qwen | 8.2 | 7.5 | $0.982 | 2/3 | 59.6s |
| #51 | Grok 4.5 low | X AI | 10.0 | 8.4 | $0.945 | 3/3 | 3.20s |