- Peringkat
- #127
- Total token output
- 16,797
- Waktu respons (rata-rata)
- 4.92s
- Total Biaya
- $1.166
Claude Opus 4.8 vs DeepSeek V4 Flash 0731 (medium)
Skor rata-rata hampir imbang di 7.3 vs 7.3. DeepSeek V4 Flash 0731 (medium) memiliki biaya benchmark lebih rendah di $0.066 vs $1.166. Claude Opus 4.8 lebih cepat di 4.92s vs 84.66s, dengan tingkat keberhasilan 63.6% vs 71.2%.
Model yang Dibandingkan
- Peringkat
- #126
- Total token output
- 550,855
- Waktu respons (rata-rata)
- 84.66s
- Total Biaya
- $0.066
Model yang direkomendasikan
DeepSeek V4 Flash 0731 (medium)
It has the best score here (7.3), while costing about 17.8x less than Claude Opus 4.8.
Perbandingan terperinci
| Metrik | Claude Opus 4.8 Claude Opus 4.8 none | DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 medium |
|---|---|---|
| Skor | 7.3 | 7.3 |
| Peringkat | #127 | #126 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.2 | 7.1 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 63.6% | 71.2% |
| Tes tidak stabil | 2 | 8 |
| Total Run | 66 | 66 |
| Biaya per hasil | 8.969 | 0.960 |
| Total Biaya | $1.166 | $0.066 |
| Harga input | $5.000 / 1M | $0.065 / 1M |
| Harga output | $25.000 / 1M | $0.180 / 1M |
| Total token input | 149,203 | 89,819 |
| Token output | 16,797 | 58,398 |
| Token penalaran | 0 | 492,457 |
| Waktu respons (rata-rata) | 4.92s | 84.66s |
| Waktu respons (maks) | 35.03s | 288.78s |
| Waktu respons (total) | 108.24s | 1862.46s |
| Parameter | ~5T total (~500B 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.
#127 Claude Opus 4.8
none- Biaya
- $0.053
- Waktu
- 22.0s
- Token
- 2,253 tok
#126 DeepSeek V4 Flash 0731
medium- Biaya
- $0.004
- Waktu
- 93.3s
- Token
- 13,252 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 Opus 4.8 | 6.5 | 10.0 | 50.0% | 0 | 3.40s | 834 | 1,472 | 0 | |
| DeepSeek V4 Flash 0731 | 8.2 | 7.9 | 83.3% | 1 | 17.95s | 698 | 2,101 | 6,715 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 5.5 | 10.0 | 33.3% | 0 | 3.29s | 10,590 | 1,332 | 0 | |
| DeepSeek V4 Flash 0731 | 6.4 | 4.4 | 77.8% | 2 | 198.78s | 6,032 | 4,109 | 160,154 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 9.8 | 10.0 | 100.0% | 0 | 26.38s | 111,760 | 11,949 | 0 | |
| DeepSeek V4 Flash 0731 | 7.3 | 5.8 | 83.3% | 1 | 150.58s | 65,118 | 40,110 | 97,296 |
| 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 Opus 4.8 | 7.3 | 5.8 | 83.3% | 1 | 1.77s | 10,503 | 308 | 0 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 5.21s | 7,290 | 287 | 1,519 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 5.3 | 7.2 | 44.4% | 1 | 1.76s | 972 | 61 | 0 | |
| DeepSeek V4 Flash 0731 | 2.9 | 7.2 | 11.1% | 1 | 203.11s | 592 | 9,333 | 154,069 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 10.0 | 10.0 | 100.0% | 0 | 3.48s | 708 | 230 | 0 | |
| DeepSeek V4 Flash 0731 | 6.1 | 3.1 | 66.7% | 1 | 12.16s | 471 | 66 | 1,589 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 9.9 | 10.0 | 100.0% | 0 | 1.37s | 909 | 95 | 0 | |
| DeepSeek V4 Flash 0731 | 8.5 | 6.8 | 83.3% | 1 | 2.42s | 706 | 109 | 580 |
| 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 Opus 4.8 | 7.7 | 10.0 | 66.7% | 0 | 2.74s | 894 | 783 | 0 | |
| DeepSeek V4 Flash 0731 | 8.2 | 7.3 | 88.9% | 1 | 65.12s | 594 | 1,530 | 66,970 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 10.0 | 10.0 | 100.0% | 0 | 5.35s | 11,775 | 355 | 0 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 4.41s | 8,178 | 374 | 152 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 3.0 | 10.0 | 0.0% | 0 | 3.41s | 258 | 212 | 0 | |
| DeepSeek V4 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 56.64s | 140 | 379 | 3,413 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V4 Flash 0731mediumvsQwen3.7 PlusnoneDeepSeek V4 Flash 0731mediumvsGLM 5.3 FlashhighClaude Opus 4.8nonevsKimi K2.6mediumClaude Opus 4.8nonevsGemini 3.1 Flash LitemediumClaude Opus 4.8nonevsGLM 5.3 FlashhighClaude Opus 4.8nonevsKAT-Coder-Pro V2.5highDeepSeek V4 Flash 0731mediumvsKAT-Coder-Pro V2.5highDeepSeek V4 Flash 0731mediumvsKAT-Coder-Pro V2.5lowClaude Opus 4.8nonevsMuse Glimmer 30BhighDeepSeek V4 Flash 0731mediumvsGLM 5.3highClaude Sonnet 4.6nonevsDeepSeek V4 Flash 0731mediumClaude Opus 4.8nonevsKAT-Coder-Pro V2.5low