Peringkat Pemrograman
Lihat model AI mana yang paling baik di Pemrograman, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Total Biaya ↓.
Model yang ditampilkan
15
Rata-rata Skor Pemrograman
6.1
Model terbaik
Grok 4.20 Multi Agent Beta 3.3
292/292
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Pemrograman | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #100 | GLM 5.3 high | Z.ai | 6.6 | 7.3 | $0.403 | 1/3 | 18.9s |
| #101 | KAT-Coder-Pro V2.5 low | Kwaipilot | 7.8 | 7.3 | $0.400 | 2/3 | 24.9s |
| #45 | Inkling Small high | Thinkingmachines | 10.0 | 8.4 | $0.398 | 3/3 | 93.2s |
| #198 | GPT-5.4 none | OpenAI | 5.5 | 5.8 | $0.397 | 1/3 | 1.62s |
| #115 | Step 3.7 Flash low | Stepfun | 8.2 | 7.1 | $0.390 | 2/3 | 9.46s |
| #187 | Gemini 3 PRO Preview medium | 3.0 | 6.0 | $0.385 | 0/3 | 0ms | |
| #57 | Inkling medium | Thinkingmachines | 8.4 | 8.0 | $0.377 | 2/3 | 25.2s |
| #4 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.5 | $0.357 | 3/3 | 11.3s |
| #165 | Mimo V2 PRO medium | Xiaomi | 6.0 | 6.3 | $0.333 | 1/3 | 94.2s |
| #266 | MiniMax M2.5 medium | Minimax | 3.4 | 4.6 | $0.327 | 0/3 | 188.6s |
| #2 | Gemini 3.7 Flash high | 10.0 | 9.8 | $0.323 | 3/3 | 13.6s | |
| #78 | GLM 5 Turbo medium | Z.ai | 8.2 | 7.6 | $0.323 | 2/3 | 45.9s |
| #110 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 6.2 | 7.2 | $0.323 | 1/3 | 125.3s |
| #85 | MiniMax M3 medium | Minimax | 6.1 | 7.5 | $0.300 | 1/3 | 144.7s |
| #143 | Gemini 3.5 Flash minimal | 5.6 | 6.7 | $0.300 | 1/3 | 2.75s |