AI BENCHY Categorie
Puzzeloplossing-ranglijst
Zie welke AI-modellen het best presteren op Puzzeloplossing, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Metriek ↑.
| Rang | Model | Bedrijf | Puzzeloplossing-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #93 | GLM 4.7 Flash medium | Z.ai | 2.9 | 4.6 | 0/3 | 12.9s |
| #76 | Kimi K2.5 none | Moonshot AI | 3.1 | 5.5 | 0/3 | 4.73s |
| #91 | Mercury 2 none | Inception | 3.1 | 4.8 | 0/3 | 533ms |
| #92 | Qwen3 Coder Next medium | Qwen | 3.1 | 4.7 | 0/3 | 2.30s |
| #97 | Qwen3.5-9B medium | Qwen | 3.1 | 4.4 | 0/3 | 33.4s |
| #83 | Mistral Small 4 none | Mistral | 3.1 | 5.2 | 0/3 | 589ms |
| #87 | Qwen3 Coder Next none | Qwen | 3.2 | 5.1 | 0/3 | 22.9s |
| #68 | gpt-oss-120b medium | OpenAI | 3.2 | 5.8 | 0/3 | 11.8s |
| #95 | Grok 4.1 Fast none | X AI | 3.2 | 4.5 | 0/3 | 1.28s |
| #90 | Qwen3.5-9B none | Qwen | 3.2 | 4.8 | 0/3 | 683ms |
| #59 | Qwen3.5-Flash none | Qwen | 3.3 | 6.2 | 0/3 | 5.90s |
| #85 | Elephant none | Openrouter | 3.3 | 5.2 | 0/3 | 849ms |
| #69 | Kimi K2.6 none | Moonshot AI | 3.4 | 5.8 | 0/3 | 1.66s |
| #73 | Mistral Small 4 medium | Mistral | 3.4 | 5.7 | 0/3 | 2.00s |
| #51 | Nemotron 3 Super medium | NVIDIA | 3.5 | 6.7 | 0/3 | 8.39s |