- Peringkat
- #132
- Total token output
- 35,547
- Waktu respons (rata-rata)
- 11.71s
- Total Biaya
- $0.256
DeepSeek V4 Pro vs Gemini 3 Flash Preview
Skor rata-rata hampir imbang di 6.8 vs 6.8. Gemini 3 Flash Preview memiliki biaya benchmark lebih rendah di $0.085 vs $0.256. Gemini 3 Flash Preview lebih cepat di 2.82s vs 11.71s, dengan tingkat keberhasilan 47.0% vs 65.2%.
- Peringkat
- #134
- Total token output
- 10,710
- Waktu respons (rata-rata)
- 2.82s
- Total Biaya
- $0.085
Model yang direkomendasikan
Gemini 3 Flash Preview
It has the best score here (6.8), while costing about 3.0x less than DeepSeek V4 Pro.
Perbandingan terperinci
| Metrik | DeepSeek V4 Pro DeepSeek V4 Pro none | Gemini 3 Flash Preview Gemini 3 Flash Preview none |
|---|---|---|
| Skor | 6.8 | 6.8 |
| Peringkat | #132 | #134 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.6 | 8.9 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 47.0% | 65.2% |
| Tes tidak stabil | 4 | 3 |
| Total Run | 66 | 66 |
| Biaya per hasil | 1.061 | 0.648 |
| Total Biaya | $0.256 | $0.085 |
| Harga input | $1.169 / 1M | $0.500 / 1M |
| Harga output | $2.337 / 1M | $3.000 / 1M |
| Total token input | 148,078 | 104,217 |
| Token output | 35,547 | 10,710 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 11.71s | 2.82s |
| Waktu respons (maks) | 119.44s | 21.19s |
| Waktu respons (total) | 257.67s | 45.05s |
| Parameter | 1.6T total (49B aktif) | ~500B total (~20B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#132 DeepSeek V4 Pro
none
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 300.0s
- Token
- 0 tok
#134 Gemini 3 Flash Preview
none- Biaya
- $0.003
- Waktu
- 5.6s
- Token
- 981 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 Pro | 3.2 | 6.1 | 16.7% | 2 | 4.02s | 540 | 1,168 | 0 | |
| Gemini 3 Flash Preview | 8.3 | 10.0 | 75.0% | 0 | 1.25s | 498 | 214 | 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 Pro | 5.6 | 10.0 | 33.3% | 0 | 13.38s | 7,275 | 5,500 | 0 | |
| Gemini 3 Flash Preview | 5.5 | 10.0 | 33.3% | 0 | 1.80s | 8,122 | 453 | 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 Pro | 7.9 | 6.9 | 66.7% | 1 | 71.59s | 122,040 | 26,362 | 0 | |
| Gemini 3 Flash Preview | 3.8 | 1.6 | 50.0% | 2 | 12.38s | 80,061 | 9,175 | 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 Pro | 10.0 | 10.0 | 100.0% | 0 | 4.61s | 7,568 | 200 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 1.41s | 7,263 | 279 | 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 Pro | 3.0 | 10.0 | 0.0% | 0 | 4.91s | 675 | 20 | 0 | |
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 879ms | 650 | 18 | 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 Pro | 5.0 | 10.0 | 0.0% | 0 | 2.05s | 471 | 126 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 1.13s | 490 | 104 | 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 Pro | 6.3 | 5.8 | 66.7% | 1 | 4.12s | 627 | 713 | 0 | |
| Gemini 3 Flash Preview | 6.4 | 5.8 | 66.7% | 1 | 1.58s | 619 | 74 | 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 Pro | 10.0 | 10.0 | 100.0% | 0 | 3.61s | 594 | 442 | 0 | |
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 1.05s | 574 | 144 | 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 Pro | 10.0 | 10.0 | 100.0% | 0 | 7.40s | 8,105 | 328 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.35s | 5,784 | 234 | 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 Pro | 3.0 | 10.0 | 0.0% | 0 | 5.76s | 183 | 688 | 0 | |
| Gemini 3 Flash Preview | 3.0 | 10.0 | 0.0% | 0 | 1.07s | 156 | 15 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3 Flash PreviewnonevsMiMo-V2.5-PromediumDeepSeek V4 PrononevsSolar Pro 4mediumDeepSeek V4 PrononevsMiMo-V2.5-PromediumDeepSeek V4 PrononevsSolar Pro 4lowDeepSeek V4 PrononevsGemma 4 26B A4BmediumTersedia gratisSeed-2.0-CodemediumvsDeepSeek V4 PrononeDeepSeek V4 PrononevsStep 3.7 FlashhighGemini 3 Flash PreviewnonevsSolar Pro 4mediumGemini 3 Flash PreviewnonevsLongCat 2.0lowGemini 3 Flash PreviewnonevsSolar Pro 4lowDeepSeek V4 PrononevsQwen3.6 FlashmediumSeed-2.0-CodemediumvsGemini 3 Flash Previewnone