- Peringkat
- #47
- Total token output
- 63,204
- Waktu respons (rata-rata)
- 12.54s
- Total Biaya
- $0.922
Claude Sonnet 5 (medium) vs DeepSeek V4 Flash 0731 (high)
Claude Sonnet 5 (medium) unggul dalam skor rata-rata dengan 8.2 vs 8.0. DeepSeek V4 Flash 0731 (high) memiliki biaya benchmark lebih rendah di $0.134 vs $0.922. Claude Sonnet 5 (medium) lebih cepat di 12.54s vs 114.94s, dengan tingkat keberhasilan 75.8% vs 75.8%.
- Peringkat
- #54
- Total token output
- 513,307
- Waktu respons (rata-rata)
- 114.94s
- Total Biaya
- $0.134
Model yang direkomendasikan
DeepSeek V4 Flash 0731 (high)
Its score stays close to the best score here (8.0 vs 8.2), while costing about 6.9x less than Claude Sonnet 5 (medium).
Perbandingan terperinci
| Metrik | Claude Sonnet 5 Claude Sonnet 5 medium | DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 high |
|---|---|---|
| Skor | 8.2 | 8.0 |
| Peringkat | #47 | #54 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.0 | 8.0 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 75.8% | 75.8% |
| Tes tidak stabil | 3 | 5 |
| Total Run | 66 | 66 |
| Biaya per hasil | 6.144 | 0.956 |
| Total Biaya | $0.922 | $0.134 |
| Harga input | $2.000 / 1M | $0.140 / 1M |
| Harga output | $10.000 / 1M | $0.280 / 1M |
| Total token input | 145,953 | 96,702 |
| Token output | 52,330 | 16,966 |
| Token penalaran | 10,874 | 496,341 |
| Waktu respons (rata-rata) | 12.54s | 114.94s |
| Waktu respons (maks) | 66.71s | 600.61s |
| Waktu respons (total) | 275.90s | 2528.65s |
| Parameter | ~1T total (~100B aktif) | 284B total (13B aktif) |
| Ketersediaan | Tertutup | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#47 Claude Sonnet 5
medium- Biaya
- $0.007
- Waktu
- 6.4s
- Token
- 832 tok
#54 DeepSeek V4 Flash 0731
high
SVG tidak valid
- Biaya
- $0.000
- Waktu
- 187.3s
- Token
- 19,048 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 10.0 | 10.0 | 100.0% | 0 | 3.80s | 834 | 1,220 | 446 | |
| DeepSeek V4 Flash 0731 | 8.7 | 7.9 | 91.7% | 1 | 13.62s | 1,488 | 542 | 10,576 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 9.0 | 7.9 | 88.9% | 1 | 17.28s | 10,590 | 13,153 | 2,379 | |
| DeepSeek V4 Flash 0731 | 6.3 | 6.3 | 55.6% | 1 | 252.67s | 7,044 | 2,160 | 191,210 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 7.3 | 6.0 | 83.3% | 1 | 51.86s | 107,934 | 23,169 | 5,371 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 87.10s | 67,283 | 11,903 | 41,397 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 10.0 | 10.0 | 100.0% | 0 | 3.16s | 10,503 | 312 | 0 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 3.65s | 7,764 | 336 | 1,259 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 5.3 | 10.0 | 33.3% | 0 | 20.54s | 972 | 12,137 | 1,994 | |
| DeepSeek V4 Flash 0731 | 3.5 | 4.4 | 33.3% | 2 | 458.65s | 700 | 104 | 215,629 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 4.8 | 3.2 | 33.3% | 1 | 4.32s | 708 | 264 | 0 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 5.64s | 708 | 72 | 533 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 9.9 | 10.0 | 100.0% | 0 | 3.10s | 909 | 318 | 269 | |
| DeepSeek V4 Flash 0731 | 9.8 | 10.0 | 100.0% | 0 | 4.46s | 1,101 | 119 | 939 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 7.7 | 10.0 | 66.7% | 0 | 2.98s | 894 | 407 | 121 | |
| DeepSeek V4 Flash 0731 | 8.2 | 7.7 | 77.8% | 1 | 9.36s | 1,305 | 397 | 6,801 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 10.0 | 10.0 | 100.0% | 0 | 10.70s | 12,351 | 433 | 90 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 5.42s | 8,889 | 357 | 451 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5 | 3.0 | 10.0 | 0.0% | 0 | 7.06s | 258 | 917 | 204 | |
| DeepSeek V4 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 110.63s | 420 | 976 | 27,546 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 Flash 0731highvsInklingmediumDeepSeek V4 Flash 0731highvsMuse Glimmer 30BxhighDeepSeek V4 Flash 0731highvsGPT-5 MinimediumDeepSeek V4 Flash 0731highvsQwen3.8 2.4T A95BlowClaude Sonnet 5mediumvsQwen3.8 2.4T A95BlowDeepSeek V4 Flash 0731highvsKimi K3maxClaude Sonnet 5mediumvsMuse Glimmer 30BxhighDeepSeek V4 Flash 0731highvsGPT-5.2 ChatnoneDeepSeek V4 Flash 0731highvsStep 3.7 FlashmediumClaude Sonnet 5mediumvsMuse Spark 1.1lowDeepSeek V4 Flash 0731highvsQwen3.8 27BlowClaude Sonnet 5mediumvsInklinghigh