- Peringkat
- #100
- Total token output
- 1,170,181
- Waktu respons (rata-rata)
- 78.20s
- Total Biaya
- $0.757
DeepSeek V4.1 Flash 1017 (max) vs Gemini 3.5 Flash (high)
Gemini 3.5 Flash (high) unggul dalam skor rata-rata dengan 8.3 vs 8.2. DeepSeek V4.1 Flash 1017 (max) memiliki biaya benchmark lebih rendah di $0.757 vs $2.737. Gemini 3.5 Flash (high) lebih cepat di 18.59s vs 78.20s, dengan tingkat keberhasilan 76.8% vs 85.5%.
Model yang Dibandingkan
- Peringkat
- #93
- Total token output
- 246,012
- Waktu respons (rata-rata)
- 18.59s
- Total Biaya
- $2.737
Model yang direkomendasikan
DeepSeek V4.1 Flash 1017 (max)
Its score stays close to the best score here (8.2 vs 8.3), while costing about 3.6x less than Gemini 3.5 Flash (high).
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 max | Gemini 3.5 Flash Gemini 3.5 Flash high |
|---|---|---|
| Skor | 8.2 | 8.3 |
| Peringkat | #100 | #93 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.2 | 9.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 76.8% | 85.5% |
| Tes tidak stabil | 5 | 2 |
| Total Run | 69 | 69 |
| Biaya per hasil | 5.041 | 14.402 |
| Total Biaya | $0.757 | $2.737 |
| 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 | 360,065 | 348,103 |
| Token output | 7,711 | 11,045 |
| Token penalaran | 1,162,470 | 234,967 |
| Waktu respons (rata-rata) | 78.20s | 18.59s |
| Waktu respons (maks) | 605.14s | 145.92s |
| Waktu respons (total) | 1798.65s | 427.52s |
| 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.
#100 DeepSeek V4.1 Flash 1017
max- Biaya
- $0.018
- Waktu
- 135.0s
- Token
- 35,163 tok
#93 Gemini 3.5 Flash
high- Biaya
- $0.208
- Waktu
- 118.2s
- Token
- 23,158 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 | 45.58s | 139,675 | 1,771 | 5,358 | |
| Gemini 3.5 Flash | 3.4 | 9.6 | 0.0% | 0 | 87.32s | 240,957 | 2,268 | 38,262 |
| 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 | 4.16s | 852 | 193 | 6,178 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.57s | 492 | 174 | 4,997 |
| 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 | 5.6 | 4.2 | 66.7% | 2 | 199.23s | 7,509 | 111 | 475,423 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 22.96s | 8,118 | 456 | 47,129 |
| 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 | 104.92s | 192,579 | 4,716 | 125,203 | |
| Gemini 3.5 Flash | 8.2 | 6.9 | 66.7% | 1 | 84.14s | 82,416 | 7,153 | 93,585 |
| 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 | 1.99s | 7,446 | 207 | 1,323 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 6.43s | 7,548 | 279 | 8,466 |
| 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 | 5.9 | 7.2 | 55.6% | 1 | 260.29s | 909 | 11 | 487,376 | |
| Gemini 3.5 Flash | 5.3 | 7.2 | 44.4% | 1 | 16.99s | 642 | 12 | 28,526 |
| 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 | 3.52s | 549 | 128 | 1,020 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.63s | 486 | 115 | 1,650 |
| 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 | 1.73s | 783 | 69 | 1,223 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.35s | 615 | 70 | 3,799 |
| 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 | 6.3 | 4.9 | 66.7% | 2 | 12.29s | 828 | 247 | 17,864 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.23s | 558 | 241 | 4,940 |
| 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 | 2.43s | 8,674 | 237 | 349 | |
| Gemini 3.5 Flash | 9.8 | 10.0 | 100.0% | 0 | 4.96s | 6,115 | 265 | 1,608 |
| 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 | 97.77s | 261 | 21 | 41,153 | |
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.94s | 156 | 12 | 2,005 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4.1 Flash 1017maxvsGemini 4 ArgonlowDeepSeek V4.1 Flash 1017maxvsGrok 4.5highGemini 3.5 FlashhighvsKimi K3maxDeepSeek V4.1 Flash 1017maxvsGLM 5.2mediumDeepSeek V4.1 Flash 1017maxvsQwen3.7 PlusmediumDeepSeek V4.1 Flash 1017maxvsLing 3.1 FlashmediumDeepSeek V4.1 Flash 1017maxvsGPT-5.6 TerramediumClaude Opus 4.8mediumvsDeepSeek V4.1 Flash 1017maxDeepSeek V4.1 Flash 1017maxvsGPT-6 LunamediumGemini 3.5 FlashhighvsGPT-6 LunamediumClaude Opus 4.8mediumvsGemini 3.5 FlashhighGemini 3.5 FlashhighvsLing 3.1 Flashmedium