- Peringkat
- #248
- Total token output
- 273,780
- Waktu respons (rata-rata)
- 14.85s
- Total Biaya
- $0.185
DeepSeek V4.1 Flash vs DeepSeek V4 Flash 0423
Skor rata-rata hampir imbang di 5.4 vs 5.4. DeepSeek V4 Flash 0423 memiliki biaya benchmark lebih rendah di $0.040 vs $0.185. DeepSeek V4.1 Flash lebih cepat di 14.85s vs 36.17s, dengan tingkat keberhasilan 34.9% vs 27.3%.
Model yang Dibandingkan
- Peringkat
- #247
- Total token output
- 100,726
- Waktu respons (rata-rata)
- 36.17s
- Total Biaya
- $0.040
Model yang direkomendasikan
DeepSeek V4 Flash 0423
It has the best score here (5.4), while costing about 4.7x less than DeepSeek V4.1 Flash.
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash DeepSeek V4.1 Flash none | DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 none |
|---|---|---|
| Skor | 5.4 | 5.4 |
| Peringkat | #248 | #247 |
| Keandalan | 9.6 | 10.0 |
| Konsistensi | 9.3 | 8.5 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 34.9% | 27.3% |
| Tes tidak stabil | 2 | 4 |
| Total Run | 66 | 66 |
| Biaya per hasil | 2.642 | 1.146 |
| Total Biaya | $0.185 | $0.040 |
| Harga input | $0.150 / 1M | $0.089 / 1M |
| Harga output | $0.600 / 1M | $0.178 / 1M |
| Total token input | 137,687 | 240,230 |
| Token output | 273,780 | 100,726 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 14.85s | 36.17s |
| Waktu respons (maks) | 247.66s | 247.27s |
| Waktu respons (total) | 326.72s | 795.83s |
| Parameter | 748B total (16B aktif) | 284B total (13B aktif) |
| Ketersediaan | Sumber terbuka | Sumber terbuka |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#248 DeepSeek V4.1 Flash
none- Biaya
- $0.021
- Waktu
- 55.4s
- Token
- 17,181 tok
#247 DeepSeek V4 Flash 0423
none- Biaya
- $0.004
- Waktu
- 157.6s
- Token
- 11,297 tok
Model teratas berdasarkan skor
Skor vs Total Biaya
Waktu respons (rata-rata)
Skor vs Waktu respons (rata-rata)
Total token output
Skor vs Total token output
Rincian Kategori
| 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 V4.1 Flash | 3.7 | 8.4 | 8.3% | 1 | 1.90s | 552 | 907 | 0 | |
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 20.18s | 540 | 174 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.5 | 10.0 | 33.3% | 0 | 83.66s | 7,284 | 263,438 | 0 | |
| DeepSeek V4 Flash 0423 | 4.2 | 7.4 | 11.1% | 1 | 17.13s | 7,279 | 9,717 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 10.37s | 116,933 | 8,699 | 0 | |
| DeepSeek V4 Flash 0423 | 4.6 | 1.8 | 66.7% | 2 | 179.61s | 214,492 | 89,681 | 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 V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 3.09s | 2,322 | 117 | 0 | |
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 23.79s | 7,290 | 195 | 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 V4.1 Flash | 7.7 | 10.0 | 66.7% | 0 | 5.46s | 684 | 21 | 0 | |
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 15.31s | 675 | 17 | 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 V4.1 Flash | 5.5 | 10.0 | 0.0% | 0 | 1.69s | 474 | 93 | 0 | |
| DeepSeek V4 Flash 0423 | 4.2 | 9.9 | 0.0% | 0 | 23.74s | 471 | 67 | 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 V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 6.81s | 633 | 62 | 0 | |
| DeepSeek V4 Flash 0423 | 6.5 | 10.0 | 50.0% | 0 | 17.54s | 627 | 321 | 0 |
| 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 V4.1 Flash | 5.3 | 7.2 | 44.4% | 1 | 1.49s | 603 | 215 | 0 | |
| DeepSeek V4 Flash 0423 | 3.1 | 7.3 | 11.1% | 1 | 23.72s | 594 | 207 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.76s | 8,016 | 219 | 0 | |
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 77.93s | 8,079 | 327 | 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 V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 1.32s | 186 | 9 | 0 | |
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 3.07s | 183 | 20 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4.1 FlashnonevsLaguna S 2.1mediumTersedia gratisDeepSeek V4 Flash 0423nonevsLaguna S 2.1mediumTersedia gratisDeepSeek V4.1 FlashnonevsKAT-Coder-Air V2.5lowDeepSeek V4 Flash 0423nonevsKAT-Coder-Air V2.5lowDeepSeek V4.1 FlashnonevsLaguna S 2.1highTersedia gratisDeepSeek V4 Flash 0423nonevsLaguna S 2.1highTersedia gratisDeepSeek V4 Flash 0423nonevsHy4 previewlowDeepSeek V4.1 FlashnonevsHy4 previewlowDeepSeek V4 Flash 0423nonevsNemotron 3.5 LightninghighTersedia gratisDeepSeek V4.1 FlashnonevsNemotron 3.5 LightninghighTersedia gratisDeepSeek V4 Flash 0423nonevsKAT-Coder-Air V2.5mediumDeepSeek V4.1 FlashnonevsKAT-Coder-Air V2.5medium