- Peringkat
- #97
- Total token output
- 211,310
- Waktu respons (rata-rata)
- 51.81s
- Total Biaya
- $0.042
DeepSeek V4 Flash 0423 (high) vs Step 3.7 Flash (medium)
Step 3.7 Flash (medium) unggul dalam skor rata-rata dengan 7.9 vs 7.6. DeepSeek V4 Flash 0423 (high) memiliki biaya benchmark lebih rendah di $0.042 vs $0.495. Step 3.7 Flash (medium) lebih cepat di 23.51s vs 51.81s, dengan tingkat keberhasilan 69.7% vs 68.2%.
Model yang Dibandingkan
- Peringkat
- #81
- Total token output
- 409,709
- Waktu respons (rata-rata)
- 23.51s
- Total Biaya
- $0.495
Model yang direkomendasikan
DeepSeek V4 Flash 0423 (high)
Its score stays close to the best score here (7.6 vs 7.9), while costing about 11.9x less than Step 3.7 Flash (medium).
Perbandingan terperinci
| Metrik | DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 high | Step 3.7 Flash Step 3.7 Flash medium |
|---|---|---|
| Skor | 7.6 | 7.9 |
| Peringkat | #97 | #81 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.5 | 8.9 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 69.7% | 68.2% |
| Tes tidak stabil | 4 | 3 |
| Total Run | 66 | 66 |
| Biaya per hasil | 0.446 | 3.801 |
| Total Biaya | $0.042 | $0.495 |
| Harga input | $0.089 / 1M | $0.200 / 1M |
| Harga output | $0.178 / 1M | $1.150 / 1M |
| Total token input | 108,480 | 114,191 |
| Token output | 37,229 | 409,709 |
| Token penalaran | 174,081 | 0 |
| Waktu respons (rata-rata) | 51.81s | 23.51s |
| Waktu respons (maks) | 218.13s | 152.83s |
| Waktu respons (total) | 1139.75s | 517.21s |
| Parameter | 284B total (13B aktif) | 198B total (11B aktif) |
| Ketersediaan | Sumber terbuka | Sumber terbuka |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#97 DeepSeek V4 Flash 0423
high- Biaya
- $0.003
- Waktu
- 93.1s
- Token
- 7,926 tok
#81 Step 3.7 Flash
medium- Biaya
- $0.006
- Waktu
- 46.2s
- Token
- 4,466 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 Flash 0423 | 8.3 | 10.0 | 75.0% | 0 | 28.51s | 540 | 140 | 7,770 | |
| Step 3.7 Flash | 8.7 | 7.9 | 91.7% | 1 | 9.65s | 756 | 32,185 | 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 Flash 0423 | 7.8 | 10.0 | 66.7% | 0 | 50.60s | 7,279 | 395 | 34,862 | |
| Step 3.7 Flash | 8.8 | 7.8 | 88.9% | 1 | 27.42s | 7,437 | 44,797 | 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 Flash 0423 | 6.4 | 5.8 | 66.7% | 1 | 104.10s | 82,663 | 4,633 | 37,533 | |
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 80.94s | 87,764 | 114,720 | 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 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 28.03s | 7,290 | 201 | 1,179 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 7,398 | 3,020 | 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 Flash 0423 | 3.6 | 7.2 | 22.2% | 1 | 115.42s | 754 | 22,778 | 79,643 | |
| Step 3.7 Flash | 5.3 | 10.0 | 33.3% | 0 | 27.26s | 837 | 52,484 | 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 Flash 0423 | 6.1 | 3.1 | 66.7% | 1 | 25.15s | 471 | 79 | 632 | |
| Step 3.7 Flash | 4.0 | 10.0 | 0.0% | 0 | 6.85s | 525 | 3,987 | 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 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 15.36s | 627 | 63 | 1,622 | |
| Step 3.7 Flash | 9.8 | 10.0 | 100.0% | 0 | 1.83s | 735 | 2,166 | 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 Flash 0423 | 8.2 | 7.2 | 88.9% | 1 | 26.11s | 594 | 196 | 1,767 | |
| Step 3.7 Flash | 5.7 | 9.9 | 33.3% | 0 | 6.19s | 756 | 15,071 | 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 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 74.73s | 8,079 | 228 | 542 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.16s | 7,746 | 2,115 | 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 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 54.46s | 183 | 8,516 | 8,531 | |
| Step 3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 113.98s | 237 | 139,164 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
GPT-5.2 ChatnonevsStep 3.7 FlashmediumKimi K3maxvsStep 3.7 FlashmediumQwen3.8 27BlowvsStep 3.7 FlashmediumGPT-5.6 TerrahighvsStep 3.7 FlashmediumClaude Opus 4.6mediumvsDeepSeek V4 Flash 0423highStep 3.7 FlashmediumvsGLM 5.2highSeed-2.0-CodelowvsDeepSeek V4 Flash 0423highDeepSeek V4 Flash 0423highvsGLM 5mediumDeepSeek V4 Flash 0423highvsSolar Pro 4xhighDeepSeek V4 Flash 0423highvsNemotron 3 UltramediumTersedia gratisClaude Opus 5nonevsDeepSeek V4 Flash 0423highDeepSeek V4 Flash 0731highvsStep 3.7 Flashmedium