- Peringkat
- #97
- Total token output
- 194,474
- Waktu respons (rata-rata)
- 25.66s
- Total Biaya
- $1.027
ERNIE-Light-DT-1.0 (high) vs DeepSeek V4.1 Flash (max)
Skor rata-rata hampir imbang di 8.6 vs 8.6. ERNIE-Light-DT-1.0 (high) memiliki biaya benchmark lebih rendah di $1.027 vs $1.204. ERNIE-Light-DT-1.0 (high) lebih cepat di 25.66s vs 61.58s, dengan tingkat keberhasilan 75.4% vs 69.6%.
Model yang Dibandingkan
- Peringkat
- #98
- Total token output
- 908,171
- Waktu respons (rata-rata)
- 61.58s
- Total Biaya
- $1.204
Model yang direkomendasikan
ERNIE-Light-DT-1.0 (high)
It has the best score here (8.6), while responding about 2.4x faster than DeepSeek V4.1 Flash (max).
Perbandingan terperinci
| Metrik | ERNIE-Light-DT-1.0 ERNIE-Light-DT-1.0 high | DeepSeek V4.1 Flash DeepSeek V4.1 Flash max |
|---|---|---|
| Skor | 8.6 | 8.6 |
| Peringkat | #97 | #98 |
| Keandalan | 9.3 | 9.4 |
| Konsistensi | 9.3 | 9.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 75.4% | 69.6% |
| Tes tidak stabil | 2 | 2 |
| Total Run | 69 | 69 |
| Biaya per hasil | 6.418 | 3.715 |
| Total Biaya | $1.027 | $1.204 |
| Harga input | $1.130 / 1M | $0.013 / 1M |
| Harga output | $3.941 / 1M | $1.320 / 1M |
| Harga baca cache | $0.113 / 1M | $0.013 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 230,563 | 414,054 |
| Token output | 6,576 | 7,635 |
| Token penalaran | 187,898 | 900,536 |
| Waktu respons (rata-rata) | 25.66s | 61.58s |
| Waktu respons (maks) | 200.80s | 335.08s |
| Waktu respons (total) | 590.18s | 1416.24s |
| Parameter | ~320B total (~18B aktif) | 748B total (16B aktif) |
| Ketersediaan | Tertutup | Sumber terbuka |
Harga cache berlaku untuk token input. Pembacaan memakai kembali prompt tersimpan; penulisan menyimpannya dan dapat menambah biaya. Token output menggunakan harga output.
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#97 ERNIE-Light-DT-1.0
high- Biaya
- $0.067
- Waktu
- 129.8s
- Token
- 16,960 tok
#98 DeepSeek V4.1 Flash
max- Biaya
- $0.066
- Waktu
- 211.0s
- Token
- 54,712 tok
Rincian Kategori
| Tugas agen | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 52.84s | 128,875 | 1,210 | 3,884 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 66.63s | 325,030 | 2,077 | 34,968 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 1.89s | 639 | 266 | 486 | |
| DeepSeek V4.1 Flash | 8.3 | 10.0 | 75.0% | 0 | 4.35s | 852 | 213 | 7,262 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 14.96s | 7,317 | 419 | 16,035 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 62.50s | 7,509 | 373 | 132,357 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 6.5 | 10.0 | 50.0% | 0 | 27.93s | 76,694 | 3,454 | 16,156 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 160.31s | 66,677 | 4,031 | 221,091 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 1.72s | 7,149 | 210 | 246 | |
| DeepSeek V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 4.56s | 2,397 | 120 | 2,047 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 3.6 | 7.2 | 22.2% | 1 | 134.82s | 759 | 220 | 149,271 | |
| DeepSeek V4.1 Flash | 3.6 | 7.2 | 22.2% | 1 | 198.41s | 909 | 27 | 384,462 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 6.5 | 3.4 | 66.7% | 1 | 2.02s | 498 | 185 | 309 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.00s | 549 | 148 | 1,093 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 2.04s | 678 | 72 | 166 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 7.64s | 783 | 63 | 2,293 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 7.7 | 10.0 | 66.7% | 0 | 2.16s | 672 | 291 | 311 | |
| DeepSeek V4.1 Flash | 5.5 | 7.1 | 44.4% | 1 | 30.82s | 828 | 339 | 54,014 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 10.0 | 10.0 | 100.0% | 0 | 4.33s | 7,075 | 231 | 149 | |
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 9.49s | 8,259 | 228 | 693 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | 3.0 | 10.0 | 0.0% | 0 | 4.23s | 207 | 18 | 885 | |
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 98.48s | 261 | 16 | 60,256 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
ERNIE-Light-DT-1.0highvsMuse EmbermaxERNIE-Light-DT-1.0highvsMuse EmberlowDeepSeek V4.1 FlashmaxvsMuse EmberlowDeepSeek V4.1 FlashmaxvsGPT-6.1 TerranoneDeepSeek V4.1 FlashmaxvsMuse Spark 1.1lowClaude Fable 5.2lowvsDeepSeek V4.1 FlashmaxERNIE-Light-DT-1.0highvsGPT-6 SollowClaude Sonnet 5.5highvsDeepSeek V4.1 FlashmaxClaude Fable 5.2highvsDeepSeek V4.1 FlashmaxERNIE-Light-DT-1.0highvsGPT-6.1 TerranoneERNIE-Light-DT-1.0highvsMuse Spark 1.1lowClaude Fable 5.2lowvsERNIE-Light-DT-1.0high