- Peringkat
- #65
- Total token output
- 444,665
- Waktu respons (rata-rata)
- 32.88s
- Total Biaya
- $0.591
DeepSeek V4.1 Flash (medium) vs GPT-5.4 (medium)
Skor rata-rata hampir imbang di 8.7 vs 8.8. DeepSeek V4.1 Flash (medium) memiliki biaya benchmark lebih rendah di $0.591 vs $2.213. GPT-5.4 (medium) lebih cepat di 24.81s vs 32.88s, dengan tingkat keberhasilan 73.9% vs 78.3%.
Model yang Dibandingkan
- Peringkat
- #62
- Total token output
- 96,502
- Waktu respons (rata-rata)
- 24.81s
- Total Biaya
- $2.213
Model yang direkomendasikan
DeepSeek V4.1 Flash (medium)
It has the best score here (8.7), while costing about 3.7x less than GPT-5.4 (medium).
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash DeepSeek V4.1 Flash medium | GPT-5.4 GPT-5.4 medium |
|---|---|---|
| Skor | 8.7 | 8.8 |
| Peringkat | #65 | #62 |
| Keandalan | 9.6 | 10.0 |
| Konsistensi | 9.3 | 8.7 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 73.9% | 78.3% |
| Tes tidak stabil | 2 | 4 |
| Total Run | 69 | 69 |
| Biaya per hasil | 1.757 | 12.535 |
| Total Biaya | $0.591 | $2.213 |
| Harga input | $0.013 / 1M | $2.500 / 1M |
| Harga output | $1.320 / 1M | $15.000 / 1M |
| Harga baca cache | $0.013 / 1M | $0.250 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 280,643 | 223,210 |
| Token output | 7,342 | 7,312 |
| Token penalaran | 437,323 | 89,190 |
| Waktu respons (rata-rata) | 32.88s | 24.81s |
| Waktu respons (maks) | 276.31s | 100.41s |
| Waktu respons (total) | 756.34s | 570.60s |
| Parameter | 748B total (16B aktif) | ~1.5T total (~100B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
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.
#65 DeepSeek V4.1 Flash
medium- Biaya
- $0.014
- Waktu
- 34.7s
- Token
- 11,541 tok
#62 GPT-5.4
medium- Biaya
- $0.214
- Waktu
- 199.6s
- Token
- 14,349 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 V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 47.59s | 192,135 | 1,932 | 11,917 | |
| GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 67.82s | 142,074 | 1,157 | 4,879 |
| 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 | 8.3 | 10.0 | 75.0% | 0 | 3.07s | 852 | 156 | 4,108 | |
| GPT-5.4 | 8.3 | 10.0 | 75.0% | 0 | 4.11s | 606 | 240 | 1,511 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 34.45s | 7,509 | 396 | 71,345 | |
| GPT-5.4 | 8.8 | 7.8 | 88.9% | 1 | 44.36s | 7,305 | 433 | 24,216 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 22.21s | 66,161 | 3,956 | 24,673 | |
| GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 29.77s | 58,038 | 4,214 | 13,351 |
| 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 | 3.77s | 2,397 | 120 | 998 | |
| GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 5.32s | 7,140 | 234 | 804 |
| 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 | 2.9 | 7.2 | 11.1% | 1 | 153.01s | 909 | 24 | 298,454 | |
| GPT-5.4 | 5.3 | 7.2 | 44.4% | 1 | 72.44s | 628 | 61 | 36,544 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 3.13s | 549 | 131 | 581 | |
| GPT-5.4 | 4.7 | 3.1 | 33.3% | 1 | 4.92s | 477 | 145 | 321 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 9.69s | 783 | 63 | 1,483 | |
| GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 3.11s | 660 | 93 | 897 |
| 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 | 8.7 | 7.7 | 88.9% | 1 | 8.01s | 828 | 293 | 12,340 | |
| GPT-5.4 | 8.2 | 7.2 | 88.9% | 1 | 9.14s | 642 | 441 | 3,815 |
| 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 | 15.33s | 8,259 | 258 | 296 | |
| GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 13.28s | 5,445 | 264 | 1,031 |
| 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 | 20.25s | 261 | 13 | 11,128 | |
| GPT-5.4 | 3.0 | 10.0 | 0.0% | 0 | 13.95s | 195 | 30 | 1,821 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4.1 FlashmediumvsKimi K3.1 PromaxDeepSeek V4.1 FlashmediumvsMuse Spark 1.2lowGPT-5.4mediumvsQwen3.8 MAXlowKimi K3.1 ProlowvsGPT-5.4mediumDeepSeek V4.1 FlashhighvsGPT-5.4mediumKimi K3.1 PromaxvsGPT-5.4mediumMuse Spark 1.2lowvsGPT-5.4mediumDeepSeek V4.1 FlashmediumvsQwen3.8 27BhighTersedia gratisGPT-5.4mediumvsPareto 26.9defaultDeepSeek V4.1 FlashmediumvsQwen3.8 MAXlowDeepSeek V4.1 FlashmediumvsKimi K3.1 ProlowDeepSeek V4.1 FlashmediumvsGPT-6 Sollow