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: Tes benar ↑.
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) |
|---|---|---|---|---|---|---|---|
| #21 | Claude Opus 5.5 high | Anthropic | 8.7 | 9.3 | $1.266 | 2/3 | 30.8s |
| #32 | Gemini 3.5 Flash medium | 7.7 | 9.0 | $0.665 | 2/3 | 2.38s | |
| #37 | GPT-5.3-Codex medium | OpenAI | 9.0 | 8.9 | $0.988 | 2/3 | 5.05s |
| #38 | Muse Spark 1.3 high | Meta | 8.7 | 8.9 | $1.653 | 2/3 | 38.4s |
| #39 | Pareto none | Unbiased | 8.2 | 8.9 | $1.172 | 2/3 | 18.2s |
| #48 | GLM 5.3 Flash max | Z.ai | 8.7 | 8.7 | $0.117 | 2/3 | 5.61s |
| #50 | Muse Spark 1.2 high | Meta | 8.2 | 8.7 | $1.771 | 2/3 | 10.1s |
| #51 | Muse Spark 1.2 medium | Meta | 8.7 | 8.6 | $1.339 | 2/3 | 9.45s |
| #52 | Muse Spark 1.1 medium | Meta | 7.9 | 8.6 | $1.420 | 2/3 | 42.5s |
| #53 | Claude Fable 5 medium | Anthropic | 7.7 | 8.6 | $3.004 | 2/3 | 5.18s |
| #56 | GPT-5.4 medium | OpenAI | 8.2 | 8.5 | $1.560 | 2/3 | 9.14s |
| #57 | DeepSeek V4.1 Flash low | DeepSeek | 8.2 | 8.5 | $0.184 | 2/3 | 9.39s |
| #59 | DeepSeek V4.1 Flash medium | DeepSeek | 8.7 | 8.5 | $0.225 | 2/3 | 8.01s |
| #61 | Muse Spark 1.2 low | Meta | 8.7 | 8.4 | $0.655 | 2/3 | 5.17s |
| #62 | Grok 4.6 medium | X AI | 8.7 | 8.4 | $1.713 | 2/3 | 16.3s |