- Peringkat
- #71
- Total token output
- 871,126
- Waktu respons (rata-rata)
- 61.35s
- Total Biaya
- $0.445
DeepSeek V4.1 Flash (max) vs GPT-6 Luna (high)
Skor rata-rata hampir imbang di 8.3 vs 8.3. GPT-6 Luna (high) memiliki biaya benchmark lebih rendah di $0.054 vs $0.445. GPT-6 Luna (high) lebih cepat di 17.53s vs 61.35s, dengan tingkat keberhasilan 68.2% vs 75.8%.
Model yang Dibandingkan
- Peringkat
- #73
- Total token output
- 91,405
- Waktu respons (rata-rata)
- 17.53s
- Total Biaya
- $0.054
Model yang direkomendasikan
GPT-6 Luna (high)
It has the best score here (8.3), while costing about 8.3x less than DeepSeek V4.1 Flash (max).
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash DeepSeek V4.1 Flash max | GPT-6 Luna GPT-6 Luna high |
|---|---|---|
| Skor | 8.3 | 8.3 |
| Peringkat | #71 | #73 |
| Keandalan | 9.1 | 10.0 |
| Konsistensi | 9.2 | 9.0 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 68.2% | 75.8% |
| Tes tidak stabil | 2 | 3 |
| Total Run | 66 | 66 |
| Biaya per hasil | 3.829 | 0.359 |
| Total Biaya | $0.445 | $0.054 |
| Harga input | $0.100 / 1M | $0.100 / 1M |
| Harga output | $0.500 / 1M | $0.500 / 1M |
| Total token input | 89,024 | 80,441 |
| Token output | 5,558 | 4,761 |
| Token penalaran | 865,568 | 86,644 |
| Waktu respons (rata-rata) | 61.35s | 17.53s |
| Waktu respons (maks) | 335.08s | 106.93s |
| Waktu respons (total) | 1349.61s | 385.74s |
| Parameter | 748B total (16B aktif) | ~400B total (~17B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#71 DeepSeek V4.1 Flash
max- Biaya
- $0.066
- Waktu
- 211.0s
- Token
- 54,712 tok
#73 GPT-6 Luna
high- Biaya
- $0.003
- Waktu
- 49.2s
- Token
- 5,231 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 V4.1 Flash | 8.3 | 10.0 | 75.0% | 0 | 4.35s | 852 | 213 | 7,262 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 2.64s | 606 | 159 | 1,358 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 62.50s | 7,509 | 373 | 132,357 | |
| GPT-6 Luna | 7.8 | 7.4 | 77.8% | 1 | 24.69s | 7,302 | 483 | 15,691 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 160.31s | 66,677 | 4,031 | 221,091 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 21.53s | 57,233 | 3,111 | 6,658 |
| 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 | 6.5 | 10.0 | 50.0% | 0 | 4.56s | 2,397 | 120 | 2,047 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 24.50s | 7,140 | 234 | 352 |
| 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 | 3.6 | 7.2 | 22.2% | 1 | 198.41s | 909 | 27 | 384,462 | |
| GPT-6 Luna | 5.9 | 7.2 | 55.6% | 1 | 51.14s | 732 | 70 | 55,170 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 4.00s | 549 | 148 | 1,093 | |
| GPT-6 Luna | 5.1 | 10.0 | 0.0% | 0 | 17.40s | 477 | 96 | 373 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 7.64s | 783 | 63 | 2,293 | |
| GPT-6 Luna | 8.4 | 6.9 | 83.3% | 1 | 1.92s | 660 | 91 | 420 |
| 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 | 5.5 | 7.1 | 44.4% | 1 | 30.82s | 828 | 339 | 54,014 | |
| GPT-6 Luna | 7.8 | 10.0 | 66.7% | 0 | 7.51s | 642 | 231 | 4,988 |
| 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 | 10.0 | 10.0 | 100.0% | 0 | 9.49s | 8,259 | 228 | 693 | |
| GPT-6 Luna | 10.0 | 10.0 | 100.0% | 0 | 6.96s | 5,454 | 256 | 261 |
| 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 | 3.0 | 10.0 | 0.0% | 0 | 98.48s | 261 | 16 | 60,256 | |
| GPT-6 Luna | 3.0 | 10.0 | 0.0% | 0 | 4.90s | 195 | 30 | 1,373 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Claude Fable 5.1mediumvsGPT-6 LunahighMuse Spark 1.1lowvsGPT-6 LunahighDeepSeek V4.1 FlashmaxvsMuse Spark 1.1lowDeepSeek V4.1 FlashmaxvsInkling SmallhighDeepSeek V4.1 FlashmaxvsGPT-6 SollowGemini 2.5 FlashmediumvsGPT-6 LunahighSeed 2.1 TurbomediumvsDeepSeek V4.1 FlashmaxDeepSeek V4.1 FlashmaxvsMiMo-V2.6-PromediumDeepSeek V4.1 FlashmaxvsQwen3.8 27BhighGPT-6 LunahighvsGLM 5.3 FlashXmaxDeepSeek V4.1 FlashmaxvsGPT-5.2mediumClaude Fable 5.1mediumvsDeepSeek V4.1 Flashmax