- Peringkat
- #126
- Total token output
- 911,334
- Waktu respons (rata-rata)
- 58.56s
- Total Biaya
- $0.589
DeepSeek V4.1 Flash 1017 (high) vs Gemini 3.5 Flash (medium)
Skor rata-rata hampir imbang di 7.8 vs 7.9. DeepSeek V4.1 Flash 1017 (high) memiliki biaya benchmark lebih rendah di $0.589 vs $1.316. Gemini 3.5 Flash (medium) lebih cepat di 11.78s vs 58.56s, dengan tingkat keberhasilan 71.0% vs 81.2%.
Model yang Dibandingkan
- Peringkat
- #121
- Total token output
- 96,655
- Waktu respons (rata-rata)
- 11.78s
- Total Biaya
- $1.316
Model yang direkomendasikan
Gemini 3.5 Flash (medium)
It has the best score here (7.9), while responding about 5.0x faster than DeepSeek V4.1 Flash 1017 (high).
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 high | Gemini 3.5 Flash Gemini 3.5 Flash medium |
|---|---|---|
| Skor | 7.8 | 7.9 |
| Peringkat | #126 | #121 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 7.8 | 9.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 71.0% | 81.2% |
| Tes tidak stabil | 6 | 2 |
| Total Run | 69 | 69 |
| Biaya per hasil | 4.530 | 7.306 |
| Total Biaya | $0.589 | $1.316 |
| Harga input | $0.150 / 1M | $1.500 / 1M |
| Harga output | $0.600 / 1M | $9.000 / 1M |
| Harga baca cache | $0.003 / 1M | $0.150 / 1M |
| Harga tulis cache | T/A | $0.084 / 1M |
| Total token input | 279,873 | 296,760 |
| Token output | 7,049 | 4,371 |
| Token penalaran | 904,285 | 92,284 |
| Waktu respons (rata-rata) | 58.56s | 11.78s |
| Waktu respons (maks) | 440.77s | 84.47s |
| Waktu respons (total) | 1346.87s | 271.03s |
| Parameter | ~748B total (~16B aktif) | ~500B total (~20B 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.
#126 DeepSeek V4.1 Flash 1017
high- Biaya
- $0.004
- Waktu
- 27.2s
- Token
- 7,593 tok
#121 Gemini 3.5 Flash
medium- Biaya
- $0.201
- Waktu
- 112.9s
- Token
- 22,371 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 43.53s | 144,680 | 1,907 | 4,293 | |
| Gemini 3.5 Flash | 2.8 | 1.6 | 33.3% | 1 | 84.47s | 227,004 | 2,205 | 32,277 |
| 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 1017 | 8.3 | 10.0 | 75.0% | 0 | 2.10s | 627 | 137 | 2,440 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.09s | 492 | 171 | 3,385 |
| 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 1017 | 4.5 | 1.4 | 66.7% | 3 | 196.67s | 7,434 | 217 | 446,179 | |
| Gemini 3.5 Flash | 7.9 | 7.5 | 77.8% | 1 | 12.63s | 8,118 | 461 | 24,939 |
| 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 37.28s | 107,806 | 3,862 | 41,936 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 44.36s | 45,684 | 516 | 8,835 |
| 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.20s | 7,446 | 207 | 1,450 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.07s | 7,548 | 279 | 3,784 |
| 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 1017 | 3.5 | 4.4 | 33.3% | 2 | 186.02s | 909 | 11 | 382,250 | |
| Gemini 3.5 Flash | 5.3 | 10.0 | 33.3% | 0 | 7.28s | 642 | 12 | 10,618 |
| 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.02s | 549 | 120 | 570 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.52s | 486 | 115 | 1,144 |
| 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.12s | 708 | 69 | 866 | |
| Gemini 3.5 Flash | 9.9 | 10.0 | 100.0% | 0 | 2.70s | 615 | 71 | 2,855 |
| 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 1017 | 5.5 | 7.4 | 44.4% | 1 | 5.70s | 828 | 235 | 7,784 | |
| Gemini 3.5 Flash | 7.7 | 10.0 | 66.7% | 0 | 2.38s | 558 | 295 | 2,747 |
| 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 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.28s | 8,625 | 267 | 305 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.81s | 5,457 | 234 | 455 |
| 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 1017 | 3.0 | 10.0 | 0.0% | 0 | 44.26s | 261 | 17 | 16,212 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 156 | 12 | 1,245 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4.1 Flash 1017highvsMuse WondermaxGemini 3.5 FlashmediumvsQwen3.8 2.4T A95BhighDeepSeek V4.1 Flash 1017highvsMiMo-V2.6-FlashmediumDeepSeek V4.1 Flash 1017highvsGrok 4.5mediumGemini 3.5 FlashmediumvsMuse WondermaxGemini 3.5 FlashmediumvsLing 3.1 FlashhighGemini 3.5 FlashmediumvsQwen3.7 MaxnoneDeepSeek V4.1 Flash 1017highvsStep 3.7 FlashmediumDeepSeek V4.1 Flash 1017highvsGrok 4.6mediumGemini 3.5 FlashmediumvsGLM 5.3highClaude Fable 5.1highvsGemini 3.5 FlashmediumGemini 3.5 FlashmediumvsGLM 5.3 FlashXmax