Peringkat Pemecahan teka-teki
Lihat model AI mana yang paling baik di Pemecahan teka-teki, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Waktu respons (rata-rata) ↓.
359/359
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Pemecahan teka-teki | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #131 | GPT-5.6 Luna medium | OpenAI | 7.8 | 7.4 | $0.072 | 2/3 | 4.04s |
| #278 | Kimi K2.5 none | Moonshot AI | 3.0 | 5.4 | $0.101 | 0/3 | 4.04s |
| #45 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.8 | $1.983 | 3/3 | 3.95s |
| #235 | Gemini 3 PRO Preview medium | 10.0 | 6.0 | $0.385 | 3/3 | 3.88s | |
| #70 | GLM 5.3 FlashX max | Z.ai | 8.2 | 8.3 | $0.508 | 2/3 | 3.88s |
| #212 | MiMo-V2-Flash medium | Xiaomi | 7.7 | 6.3 | $0.043 | 2/3 | 3.87s |
| #313 | Trinity Large Thinking high | Arcee AI | 4.7 | 4.8 | $0.592 | 0/3 | 3.84s |
| #117 | GPT-5.4 Nano medium | OpenAI | 4.1 | 7.5 | $0.142 | 0/3 | 3.79s |
| #99 | GPT-5.6 Terra medium | OpenAI | 8.4 | 7.8 | $0.523 | 2/3 | 3.78s |
| #333 | Hunter Alpha none | OpenRouter | 5.8 | 4.2 | $0.000 | 1/3 | 3.71s |
| #115 | Claude Opus 5 none | Anthropic | 7.7 | 7.5 | $1.550 | 2/3 | 3.66s |
| #178 | DeepSeek V4 Pro none | DeepSeek | 10.0 | 6.8 | $0.210 | 3/3 | 3.61s |
| #5 | GPT-6 Astra high | OpenAI | 10.0 | 9.9 | $3.474 | 3/3 | 3.60s |
| #217 | GPT-5.6 Luna low | OpenAI | 7.6 | 6.2 | $0.051 | 2/3 | 3.59s |
| #114 | Nemotron 3 Ultra medium | NVIDIA | 5.5 | 7.6 | $0.567 | 1/3 | 3.54s |