- Peringkat
- #256
- Total token output
- 42,099
- Waktu respons (rata-rata)
- 17.89s
- Total Biaya
- $0.054
DeepSeek V3.2 vs Mercury 2.5 Preview
DeepSeek V3.2 unggul dalam skor rata-rata dengan 5.0 vs 4.9. Mercury 2.5 Preview memiliki biaya benchmark lebih rendah di $0.018 vs $0.054. Mercury 2.5 Preview lebih cepat di 3.51s vs 17.89s, dengan tingkat keberhasilan 36.4% vs 30.3%.
- Peringkat
- #259
- Total token output
- 82,585
- Waktu respons (rata-rata)
- 3.51s
- Total Biaya
- $0.018
Model yang direkomendasikan
Mercury 2.5 Preview
Its score stays close to the best score here (4.9 vs 5.0), while costing about 3.0x less than DeepSeek V3.2.
Perbandingan terperinci
| Metrik | DeepSeek V3.2 DeepSeek V3.2 none | Mercury 2.5 Preview Mercury 2.5 Preview none |
|---|---|---|
| Skor | 5.0 | 4.9 |
| Peringkat | #256 | #259 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.1 | 8.3 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 36.4% | 30.3% |
| Tes tidak stabil | 5 | 5 |
| Total Run | 66 | 66 |
| Biaya per hasil | 0.870 | 0.440 |
| Total Biaya | $0.054 | $0.018 |
| Harga input | $0.269 / 1M | $0.040 / 1M |
| Harga output | $0.400 / 1M | $0.150 / 1M |
| Total token input | 135,831 | 130,296 |
| Token output | 42,099 | 82,585 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 17.89s | 3.51s |
| Waktu respons (maks) | 115.89s | 60.70s |
| Waktu respons (total) | 393.53s | 77.28s |
| Parameter | 671B total (37B aktif) | ~100B |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#256 DeepSeek V3.2
none- Biaya
- $0.002
- Waktu
- 7.0s
- Token
- 1,046 tok
#259 Mercury 2.5 Preview
none
SVG tidak valid
- Biaya
- $0.001
- Waktu
- 3.3s
- Token
- 3,122 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 V3.2 | 3.2 | 8.0 | 8.3% | 1 | 9.35s | 494 | 1,073 | 0 | |
| Mercury 2.5 Preview | 3.8 | 8.3 | 16.7% | 1 | 655ms | 812 | 256 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 3.1 | 6.9 | 11.1% | 1 | 14.54s | 7,279 | 4,528 | 0 | |
| Mercury 2.5 Preview | 4.7 | 7.9 | 22.2% | 1 | 459ms | 7,850 | 650 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | 4.8 | 10.0 | 0.0% | 0 | 113.53s | 109,626 | 33,819 | 0 | |
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 31.28s | 101,129 | 80,273 | 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 V3.2 | 6.3 | 5.8 | 66.7% | 1 | 9.42s | 7,890 | 1,710 | 0 | |
| Mercury 2.5 Preview | 6.3 | 5.8 | 66.7% | 1 | 1.04s | 8,333 | 672 | 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 V3.2 | 3.0 | 10.0 | 0.0% | 0 | 1.48s | 675 | 23 | 0 | |
| Mercury 2.5 Preview | 3.6 | 7.2 | 22.2% | 1 | 631ms | 875 | 40 | 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 V3.2 | 4.7 | 1.6 | 66.7% | 1 | 9.32s | 314 | 43 | 0 | |
| Mercury 2.5 Preview | 5.0 | 10.0 | 0.0% | 0 | 482ms | 544 | 85 | 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 V3.2 | 10.0 | 10.0 | 100.0% | 0 | 1.52s | 627 | 66 | 0 | |
| Mercury 2.5 Preview | 6.3 | 10.0 | 50.0% | 0 | 1.26s | 753 | 73 | 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 V3.2 | 7.6 | 7.2 | 77.8% | 1 | 6.91s | 424 | 298 | 0 | |
| Mercury 2.5 Preview | 5.6 | 7.4 | 44.4% | 1 | 684ms | 796 | 292 | 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 V3.2 | 10.0 | 10.0 | 100.0% | 0 | 11.85s | 8,319 | 522 | 0 | |
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 1.29s | 8,969 | 229 | 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 V3.2 | 3.0 | 10.0 | 0.0% | 0 | 17.23s | 183 | 17 | 0 | |
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 419ms | 235 | 15 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
DeepSeek V3.2nonevsLaguna S 2.1lowTersedia gratisDeepSeek V3.2nonevsMercury 2.5 PreviewlowDeepSeek V3.2nonevsMiniMax M2.7mediumMercury 2.5 PreviewnonevsLaguna S 2.1lowTersedia gratisMercury 2.5 PreviewnonevsNemotron 3.5 LightninglowTersedia gratisMercury 2.5 PreviewnonevsMiniMax M2.7mediumTrinity Large ThinkinghighvsMercury 2.5 PreviewnoneDeepSeek V3.2nonevsGranite 4.2 8BlowDeepSeek V3.2nonevsMistral Small 4mediumDeepSeek V3.2nonevsNemotron 3.5 LightningmediumTersedia gratisDeepSeek V3.2nonevsNemotron 3.5 LightninglowTersedia gratisDeepSeek V3.2nonevsGranite 4.2 8Bmedium