#58 DeepSeek V4 Pro
none
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 300.0s
- Token
- 0 tok
AI BENCHY Compare
DeepSeek: DeepSeek V4 Pro vs Google: Gemini 2.5 Flash
Ringkasan
Perbandingan benchmark DeepSeek V4 Pro vs Gemini 2.5 Flash: Gemini 2.5 Flash unggul dalam skor rata-rata dengan 8.2 vs 7.2. DeepSeek V4 Pro memiliki biaya benchmark lebih rendah di $0.034 vs $0.379. DeepSeek V4 Pro lebih cepat di 6.41s vs 15.49s, dengan tingkat keberhasilan 52.4% vs 69.8%.
Model yang direkomendasikan: DeepSeek V4 Pro - It offers the best overall trade-off: a competitive score (7.2), lower cost than Gemini 2.5 Flash, and balanced response time.
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-06-18
| Metrik | DeepSeek V4 Pro DeepSeek V4 Pro none | Gemini 2.5 Flash Gemini 2.5 Flash medium |
|---|---|---|
| Skor | 7.2 | 8.2 |
| Peringkat | #58 | #24 |
| Keandalan | 9.9 | 10.0 |
| Konsistensi | 8.8 | 9.6 |
| Tes benar | ||
| Tingkat lulus per percobaan | 52.4% | 69.8% |
| Tes tidak stabil | 3 | 1 |
| Total Run | 63 | 63 |
| Biaya per hasil | 0.333 | 2.701 |
| Total Biaya | $0.034 | $0.379 |
| Harga input | $0.435 / 1M | $0.300 / 1M |
| Harga output | $0.870 / 1M | $2.500 / 1M |
| Total token input | 53,558 | 34,476 |
| Token output | 11,424 | 1,930 |
| Token penalaran | 0 | 145,145 |
| Waktu respons (rata-rata) | 6.41s | 15.49s |
| Waktu respons (maks) | 30.09s | 95.48s |
| Waktu respons (total) | 134.66s | 325.39s |
Showcase generasi
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#24 Gemini 2.5 Flash
medium
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 274.0s
- Token
- 0 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 2.5 Flash | 8.4 | 10.0 | 75.0% | 0 | 6.30s | 492 | 255 | 10,233 |
| 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 2.5 Flash | 7.8 | 10.0 | 66.7% | 0 | 41.01s | 6,669 | 543 | 32,303 |
| 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 | 9.5 | 10.0 | 100.0% | 0 | 23.74s | 27,529 | 2,235 | 0 | |
| Gemini 2.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 28.44s | 12,522 | 303 | 11,922 |
| 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 2.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.06s | 7,257 | 279 | 2,325 |
| 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 | 5.3 | 10.0 | 33.3% | 0 | 3.72s | 666 | 24 | 0 | |
| Gemini 2.5 Flash | 5.9 | 7.2 | 55.6% | 1 | 37.34s | 633 | 18 | 80,702 |
| 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 2.5 Flash | 4.8 | 10.0 | 0.0% | 0 | 4.86s | 486 | 92 | 1,899 |
| 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 2.5 Flash | 9.8 | 10.0 | 100.0% | 0 | 2.62s | 615 | 69 | 1,203 |
| 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 2.5 Flash | 7.7 | 10.0 | 66.7% | 0 | 3.18s | 558 | 126 | 2,499 |
| 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 2.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 6.20s | 5,088 | 234 | 1,140 |
| 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 2.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 2.76s | 156 | 11 | 919 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 PrononevsGemma 4 26B A4BmediumTersedia gratisDeepSeek V4 FlashhighvsGemini 2.5 FlashmediumDeepSeek V4 PrononevsStep 3.7 FlashhighDeepSeek V4 PrononevsGLM 5.1mediumDeepSeek V4 PrononevsKimi K2.7 CodemediumDeepSeek V4 PrononevsGrok 4.20mediumDeepSeek V4 PrononevsGemini 3 Flash PreviewlowDeepSeek V4 PrononevsMiMo-V2.5-PromediumSeed-2.0-MinimediumvsDeepSeek V4 PrononeGemini 2.5 FlashmediumvsGPT-5.2 ChatnoneDeepSeek V4 PrononevsQwen3.6 FlashmediumDeepSeek V4 PrononevsGPT-5.4 Nanomedium