- Peringkat
- #279
- Total token output
- 39,789
- Waktu respons (rata-rata)
- 27.42s
- Total Biaya
- $0.053
DeepSeek V4 Flash 0731 vs GPT-6 Luna (medium)
GPT-6 Luna (medium) unggul dalam skor rata-rata dengan 8.3 vs 6.2. GPT-6 Luna (medium) memiliki biaya benchmark lebih rendah di $0.047 vs $0.053. GPT-6 Luna (medium) lebih cepat di 18.07s vs 27.42s, dengan tingkat keberhasilan 30.4% vs 73.9%.
Model yang Dibandingkan
- Peringkat
- #103
- Total token output
- 53,161
- Waktu respons (rata-rata)
- 18.07s
- Total Biaya
- $0.047
Model yang direkomendasikan
GPT-6 Luna (medium)
It has the best score here (8.3), while responding about 1.5x faster than DeepSeek V4 Flash 0731.
Perbandingan terperinci
| Metrik | DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 none | GPT-6 Luna GPT-6 Luna medium |
|---|---|---|
| Skor | 6.2 | 8.3 |
| Peringkat | #279 | #103 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.7 | 8.9 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 30.4% | 73.9% |
| Tes tidak stabil | 4 | 3 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.826 | 0.313 |
| Total Biaya | $0.053 | $0.047 |
| Harga input | $0.005 / 1M | $0.100 / 1M |
| Harga output | $1.280 / 1M | $0.500 / 1M |
| Harga baca cache | $0.005 / 1M | $0.010 / 1M |
| Harga tulis cache | T/A | $0.125 / 1M |
| Total token input | 349,876 | 203,193 |
| Token output | 39,789 | 5,751 |
| Token penalaran | 0 | 47,410 |
| Waktu respons (rata-rata) | 27.42s | 18.07s |
| Waktu respons (maks) | 387.15s | 66.44s |
| Waktu respons (total) | 630.70s | 415.53s |
| Parameter | 284B total (13B aktif) | ~400B total (~17B aktif) |
| Ketersediaan | Tertutup | 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.
#279 DeepSeek V4 Flash 0731
none- Biaya
- $0.004
- Waktu
- 198.4s
- Token
- 14,316 tok
#103 GPT-6 Luna
medium- Biaya
- $0.002
- Waktu
- 23.6s
- Token
- 2,966 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 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 174.89s | 255,310 | 14,363 | 0 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 66.44s | 124,247 | 1,116 | 6,891 |
| 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 Flash 0731 | 3.4 | 8.3 | 8.3% | 1 | 4.19s | 540 | 801 | 0 | |
| GPT-6 Luna | 8.3 | 10.0 | 75.0% | 0 | 4.32s | 606 | 156 | 875 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 4.3 | 10.0 | 0.0% | 0 | 1.72s | 7,275 | 505 | 0 | |
| GPT-6 Luna | 6.6 | 4.6 | 77.8% | 2 | 23.63s | 7,302 | 438 | 10,222 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | 3.7 | 1.8 | 50.0% | 2 | 202.44s | 65,531 | 22,822 | 0 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 22.65s | 55,738 | 3,052 | 4,096 |
| 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 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 2.37s | 7,290 | 199 | 0 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 26.09s | 7,140 | 234 | 268 |
| 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 Flash 0731 | 5.3 | 10.0 | 33.3% | 0 | 1.17s | 675 | 26 | 0 | |
| GPT-6 Luna | 5.9 | 7.2 | 55.6% | 1 | 22.71s | 732 | 70 | 19,191 |
| 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 Flash 0731 | 4.4 | 9.9 | 0.0% | 0 | 3.22s | 471 | 153 | 0 | |
| GPT-6 Luna | 4.4 | 9.9 | 0.0% | 0 | 28.25s | 477 | 91 | 289 |
| 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 Flash 0731 | 5.0 | 6.8 | 33.3% | 1 | 1.42s | 627 | 69 | 0 | |
| GPT-6 Luna | 9.8 | 10.0 | 100.0% | 0 | 13.24s | 660 | 89 | 409 |
| 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 Flash 0731 | 3.2 | 9.9 | 0.0% | 0 | 2.74s | 594 | 302 | 0 | |
| GPT-6 Luna | 7.7 | 10.0 | 66.7% | 0 | 9.78s | 642 | 211 | 3,189 |
| 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 Flash 0731 | 9.5 | 10.0 | 100.0% | 0 | 4.61s | 11,380 | 536 | 0 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 4.84s | 5,454 | 264 | 249 |
| 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 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 1.85s | 183 | 13 | 0 | |
| GPT-6 Luna | 3.0 | 10.0 | 0.0% | 0 | 6.39s | 195 | 30 | 1,731 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 Flash 0731nonevsKAT-Coder-Pro V2.5mediumGemini 4 ArgonlowvsGPT-6 LunamediumDeepSeek V4.1 Flash 1017maxvsGPT-6 LunamediumGPT-6 LunamediumvsGrok 4.5highDeepSeek V4 Flash 0731nonevsSpace Bunny AlphaxhighClaude Fable 5.1lowvsDeepSeek V4 Flash 0731noneKimi K3maxvsGPT-6 LunamediumGemini 3.5 FlashhighvsGPT-6 LunamediumClaude Haiku 5.5highvsGPT-6 LunamediumDeepSeek V4 Flash 0731nonevsGrok 4.20mediumTrinity Large ThinkinglowvsDeepSeek V4 Flash 0731noneDeepSeek V4 Flash 0731nonevsSpace Bunny Alphamedium