Kategori AI BENCHY
Peringkat Kepatuhan instruksi
Lihat model AI mana yang paling baik di Kepatuhan instruksi, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Metrik ↑.
| Peringkat | Model | Perusahaan | Skor Kepatuhan instruksi | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #117 | Qwen3.5-35B-A3B none | Qwen | 6.3 | 5.6 | 1/2 | 809ms |
| #127 | Grok 4.20 none | X AI | 6.3 | 5.4 | 1/2 | 445ms |
| #128 | Qwen3.6 Flash none | Qwen | 6.3 | 5.4 | 1/2 | 1.10s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 6.3 | 5.3 | 1/2 | 513ms |
| #140 | Qwen3 Coder Next none | Qwen | 6.3 | 4.9 | 1/2 | 7.78s |
| #141 | Nemotron 3 Super none | NVIDIA | 6.3 | 4.9 | 1/2 | 804ms |
| #144 | GPT-5.4 Mini none | OpenAI | 6.3 | 4.9 | 1/2 | 728ms |
| #147 | GPT-4o-mini none | OpenAI | 6.3 | 4.8 | 1/2 | 1.11s |
| #148 | GPT-5.4 Nano none | OpenAI | 6.3 | 4.7 | 1/2 | 784ms |
| #150 | Qwen3 Coder Next medium | Qwen | 6.3 | 4.6 | 1/2 | 7.49s |
| #160 | LFM2-24B-A2B none | Liquid | 6.3 | 4.2 | 1/2 | 752ms |
| #113 | DeepSeek V4 Pro none | DeepSeek | 6.3 | 5.7 | 1/2 | 8.23s |
| #145 | Laguna M.1 none | Poolside | 6.3 | 4.8 | 1/2 | 683ms |
| #156 | Hy3 preview none | Tencent | 6.3 | 4.4 | 1/2 | 13.0s |
| #116 | Hunter Alpha none | OpenRouter | 6.4 | 5.7 | 1/2 | 2.82s |