Kategori AI BENCHY
Peringkat Parsing dan ekstraksi data
Lihat model AI mana yang paling baik di Parsing dan ekstraksi data, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Tes benar ↑.
| Peringkat | Model | Perusahaan | Skor Parsing dan ekstraksi data | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #113 | DeepSeek V4 Pro none | DeepSeek | 6.9 | 5.7 | 1/2 | 30.5s |
| #118 | Qwen3.6 27B none | Qwen | 7.3 | 5.6 | 1/2 | 2.06s |
| #119 | Cobuddy medium | Baidu | 6.3 | 5.6 | 1/2 | 17.4s |
| #122 | GLM 4.7 Flash none | Z.ai | 7.3 | 5.5 | 1/2 | 4.82s |
| #126 | gpt-oss-120b none | OpenAI | 6.5 | 5.4 | 1/2 | 7.12s |
| #130 | MiniMax M2.7 medium | Minimax | 6.3 | 5.3 | 1/2 | 21.9s |
| #132 | Mistral Small 4 medium | Mistral | 7.3 | 5.3 | 1/2 | 1.23s |
| #133 | DeepSeek V3.2 none | DeepSeek | 6.3 | 5.2 | 1/2 | 9.42s |
| #135 | Kimi K2.5 none | Moonshot AI | 7.3 | 5.2 | 1/2 | 42.1s |
| #136 | Elephant Alpha medium | Openrouter | 6.5 | 5.1 | 1/2 | 979ms |
| #137 | Elephant Alpha none | Openrouter | 6.5 | 5.1 | 1/2 | 1.04s |
| #138 | Ling-2.6-flash none | Inclusionai | 6.5 | 5.0 | 1/2 | 8.48s |
| #140 | Qwen3 Coder Next none | Qwen | 6.5 | 4.9 | 1/2 | 1.32s |
| #143 | MiMo-V2.5 none | Xiaomi | 6.5 | 4.9 | 1/2 | 1.01s |
| #148 | GPT-5.4 Nano none | OpenAI | 6.5 | 4.7 | 1/2 | 1.11s |