- Peringkat
- #153
- Total token output
- 237,822
- Waktu respons (rata-rata)
- 88.15s
- Total Biaya
- $0.306
DeepSeek V4 Flash 0731 (low) vs DeepSeek V4 Pro 0423
Skor rata-rata hampir imbang di 7.4 vs 7.4. DeepSeek V4 Pro 0423 memiliki biaya benchmark lebih rendah di $0.083 vs $0.306. DeepSeek V4 Pro 0423 lebih cepat di 14.05s vs 88.15s, dengan tingkat keberhasilan 71.0% vs 49.3%.
Model yang Dibandingkan
- Peringkat
- #158
- Total token output
- 46,004
- Waktu respons (rata-rata)
- 14.05s
- Total Biaya
- $0.083
Model yang direkomendasikan
DeepSeek V4 Pro 0423
It has the best score here (7.4), while costing about 3.7x less than DeepSeek V4 Flash 0731 (low).
Perbandingan terperinci
| Metrik | DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 low | DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 none |
|---|---|---|
| Skor | 7.4 | 7.4 |
| Peringkat | #153 | #158 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.0 | 8.7 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 71.0% | 49.3% |
| Tes tidak stabil | 6 | 4 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.840 | 2.341 |
| Total Biaya | $0.306 | $0.083 |
| Harga input | $0.005 / 1M | $0.209 / 1M |
| Harga output | $1.280 / 1M | $0.418 / 1M |
| Harga baca cache | $0.005 / 1M | $0.018 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 231,356 | 304,186 |
| Token output | 43,054 | 40,118 |
| Token penalaran | 370,981 | 5,886 |
| Waktu respons (rata-rata) | 88.15s | 14.05s |
| Waktu respons (maks) | 438.65s | 119.44s |
| Waktu respons (total) | 2027.36s | 323.17s |
| Parameter | 284B total (13B aktif) | 1.6T total (49B aktif) |
| Ketersediaan | Tertutup | Sumber terbuka |
Harga cache berlaku untuk token input. Pembacaan memakai kembali prompt tersimpan; penulisan menyimpannya dan dapat menambah biaya. Token output menggunakan harga output.
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#153 DeepSeek V4 Flash 0731
low
No output was saved. The original provider response or failure reason is unavailable.
- Biaya
- $0.000
- Waktu
- 78.1s
- Token
- 8,090 tok
#158 DeepSeek V4 Pro 0423
none
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Biaya
- $0.000
- Waktu
- 300.0s
- Token
- 0 tok
Rincian Kategori
| Tugas agen | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 4.7 | 1.6 | 66.7% | 1 | 321.18s | 138,011 | 7,331 | 20,715 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 65.50s | 156,108 | 10,457 | 0 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 8.2 | 7.9 | 83.3% | 1 | 10.08s | 540 | 1,833 | 6,605 | |
| DeepSeek V4 Pro 0423 | 3.2 | 6.1 | 16.7% | 2 | 4.02s | 540 | 944 | 224 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 7.3 | 5.1 | 77.8% | 2 | 163.31s | 5,953 | 782 | 86,028 | |
| DeepSeek V4 Pro 0423 | 5.6 | 10.0 | 33.3% | 0 | 13.38s | 7,275 | 1,436 | 4,064 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 9.8 | 10.0 | 100.0% | 0 | 54.25s | 68,913 | 8,230 | 22,729 | |
| DeepSeek V4 Pro 0423 | 7.9 | 6.9 | 66.7% | 1 | 71.59s | 122,040 | 26,362 | 0 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 4.35s | 7,290 | 305 | 995 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 4.61s | 7,568 | 200 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 255.51s | 657 | 20,100 | 171,883 | |
| DeepSeek V4 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 4.91s | 675 | 20 | 0 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 6.5 | 3.4 | 66.7% | 1 | 7.63s | 471 | 81 | 1,181 | |
| DeepSeek V4 Pro 0423 | 5.0 | 10.0 | 0.0% | 0 | 2.05s | 471 | 126 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 9.9 | 10.0 | 100.0% | 0 | 3.01s | 627 | 94 | 644 | |
| DeepSeek V4 Pro 0423 | 6.3 | 5.8 | 66.7% | 1 | 4.12s | 627 | 63 | 650 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 8.0 | 7.6 | 77.8% | 1 | 9.08s | 594 | 414 | 4,808 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 3.61s | 594 | 167 | 275 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 4.44s | 8,178 | 367 | 186 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 7.40s | 8,105 | 328 | 0 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 246.86s | 122 | 3,517 | 55,207 | |
| DeepSeek V4 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 5.76s | 183 | 15 | 673 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 Flash 0731lowvsQwen3.6 FlashmediumDeepSeek V4 Pro 0423nonevsInklingmediumTersedia gratisDeepSeek V4 Flash 0731lowvsGPT-5.6 LunamediumSeed-2.0-CodemediumvsDeepSeek V4 Flash 0731lowDeepSeek V4 Flash 0731lowvsGLM 5.3 FlashXhighDeepSeek V4 Pro 0423nonevsInkling SmallhighTersedia gratisDeepSeek V4 Flash 0731lowvsInkling SmallhighTersedia gratisDeepSeek V4 Pro 0423nonevsGemma 4 26B A4BmediumTersedia gratisDeepSeek V4 Pro 0423nonevsGrok 4.7lowDeepSeek V4 Pro 0423nonevsGLM 5.3 FlashXhighSeed-2.0-CodemediumvsDeepSeek V4 Pro 0423noneDeepSeek V4 Pro 0423nonevsQwen3.6 Flashmedium