Kategori AI BENCHY
Peringkat Pemrograman
Lihat model AI mana yang paling baik di Pemrograman, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Tes benar ↓.
| Peringkat | Model | Perusahaan | Skor Pemrograman | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #52 | MiMo-V2-Omni none | Xiaomi | 6.6 | 6.5 | 0/1 | 1.72s |
| #54 | GPT-5 Nano medium | OpenAI | 6.7 | 6.3 | 0/1 | 40.7s |
| #57 | Gemma 4 26B A4B none | 4.7 | 6.2 | 0/1 | 7.07s | |
| #61 | DeepSeek V3.2 none | DeepSeek | 2.4 | 6.1 | 0/1 | 7.63s |
| #65 | gpt-oss-120b medium | OpenAI | 4.3 | 5.8 | 0/1 | 26.3s |
| #66 | Qwen3.5-122B-A10B none | Qwen | 4.3 | 5.7 | 0/1 | 3.44s |
| #67 | MiniMax M2.5 medium | Minimax | 3.0 | 5.7 | 0/1 | 0ms |
| #68 | Hunter Alpha none | OpenRouter | 3.0 | 5.7 | 0/1 | 0ms |
| #69 | Mistral Small 4 medium | Mistral | 6.7 | 5.7 | 0/1 | 30.5s |
| #70 | GLM 4.7 Flash none | Z.ai | 6.4 | 5.6 | 0/1 | 5.57s |
| #71 | GLM 5.1 none | Z.ai | 5.1 | 5.6 | 0/1 | 9.79s |
| #73 | GLM 5 Turbo none | Z.ai | 5.3 | 5.5 | 0/1 | 3.93s |
| #74 | Trinity Large Preview none | Arcee AI | 6.3 | 5.3 | 0/1 | 39.5s |
| #75 | Grok 4.20 Beta none | X AI | 5.5 | 5.3 | 0/1 | 1.14s |
| #77 | Grok 4.20 none | X AI | 3.4 | 5.2 | 0/1 | 1.22s |