- Peringkat
- #131
- Total token output
- 211,343
- Waktu respons (rata-rata)
- 91.29s
- Total Biaya
- $0.149
DeepSeek V4 Pro 0423 (high) vs GLM 5.3 FlashX Legal (high)
GLM 5.3 FlashX Legal (high) unggul dalam skor rata-rata dengan 8.2 vs 8.1. DeepSeek V4 Pro 0423 (high) memiliki biaya benchmark lebih rendah di $0.149 vs $0.521. GLM 5.3 FlashX Legal (high) lebih cepat di 35.19s vs 91.29s, dengan tingkat keberhasilan 65.2% vs 72.5%.
Model yang Dibandingkan
- Peringkat
- #127
- Total token output
- 345,985
- Waktu respons (rata-rata)
- 35.19s
- Total Biaya
- $0.521
Model yang direkomendasikan
DeepSeek V4 Pro 0423 (high)
Its score stays close to the best score here (8.1 vs 8.2), while costing about 3.5x less than GLM 5.3 FlashX Legal (high).
Perbandingan terperinci
| Metrik | DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 high | GLM 5.3 FlashX Legal GLM 5.3 FlashX Legal high |
|---|---|---|
| Skor | 8.1 | 8.2 |
| Peringkat | #131 | #127 |
| Keandalan | 10.0 | 9.7 |
| Konsistensi | 7.8 | 8.6 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 65.2% | 72.5% |
| Tes tidak stabil | 6 | 4 |
| Total Run | 69 | 69 |
| Biaya per hasil | 3.717 | 3.473 |
| Total Biaya | $0.149 | $0.521 |
| Harga input | $0.209 / 1M | $0.370 / 1M |
| Harga output | $0.418 / 1M | $1.250 / 1M |
| Harga baca cache | $0.018 / 1M | $0.075 / 1M |
| Harga tulis cache | T/A | T/A |
| Total token input | 287,061 | 238,713 |
| Token output | 32,056 | 7,034 |
| Token penalaran | 196,607 | 338,951 |
| Waktu respons (rata-rata) | 91.29s | 35.19s |
| Waktu respons (maks) | 416.76s | 298.81s |
| Waktu respons (total) | 2099.56s | 809.47s |
| Parameter | 1.6T total (49B aktif) | ~320B total (~18B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
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.
#131 DeepSeek V4 Pro 0423
high- Biaya
- $0.023
- Waktu
- 257.6s
- Token
- 14,870 tok
#127 GLM 5.3 FlashX Legal
high- Biaya
- $0.018
- Waktu
- 103.8s
- Token
- 13,703 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 |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 64.54s | 196,304 | 9,128 | 10,091 | |
| GLM 5.3 FlashX Legal | 10.0 | 10.0 | 100.0% | 0 | 78.95s | 140,782 | 1,206 | 13,815 |
| 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 Pro 0423 | 5.7 | 5.9 | 58.3% | 2 | 25.70s | 536 | 149 | 3,214 | |
| GLM 5.3 FlashX Legal | 8.2 | 7.9 | 83.3% | 1 | 1.50s | 639 | 282 | 456 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 6.3 | 8.7 | 33.3% | 0 | 243.00s | 5,090 | 383 | 84,580 | |
| GLM 5.3 FlashX Legal | 8.2 | 7.2 | 88.9% | 1 | 27.50s | 7,317 | 397 | 31,799 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 78.99s | 66,082 | 4,582 | 25,404 | |
| GLM 5.3 FlashX Legal | 6.9 | 5.9 | 66.7% | 1 | 22.42s | 73,021 | 3,779 | 11,384 |
| 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 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 25.03s | 7,690 | 274 | 2,166 | |
| GLM 5.3 FlashX Legal | 10.0 | 10.0 | 100.0% | 0 | 1.32s | 7,149 | 210 | 358 |
| 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 Pro 0423 | 3.6 | 7.2 | 22.2% | 1 | 249.47s | 578 | 16,870 | 58,188 | |
| GLM 5.3 FlashX Legal | 3.0 | 10.0 | 0.0% | 0 | 188.77s | 759 | 195 | 278,113 |
| 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 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 8.83s | 471 | 115 | 1,013 | |
| GLM 5.3 FlashX Legal | 4.8 | 3.2 | 33.3% | 1 | 1.78s | 498 | 204 | 214 |
| 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 Pro 0423 | 7.8 | 6.6 | 83.3% | 1 | 8.73s | 627 | 66 | 2,726 | |
| GLM 5.3 FlashX Legal | 10.0 | 10.0 | 100.0% | 0 | 1.53s | 678 | 72 | 240 |
| 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 Pro 0423 | 6.9 | 4.9 | 77.8% | 2 | 56.85s | 591 | 178 | 2,563 | |
| GLM 5.3 FlashX Legal | 10.0 | 10.0 | 100.0% | 0 | 2.45s | 672 | 411 | 479 |
| 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 Pro 0423 | 9.8 | 10.0 | 100.0% | 0 | 15.92s | 8,909 | 295 | 701 | |
| GLM 5.3 FlashX Legal | 10.0 | 10.0 | 100.0% | 0 | 7.41s | 6,991 | 225 | 98 |
| 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 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 34.01s | 183 | 16 | 5,961 | |
| GLM 5.3 FlashX Legal | 3.0 | 10.0 | 0.0% | 0 | 8.62s | 207 | 53 | 1,995 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
GPT-5.6 TerramediumvsGLM 5.3 FlashX LegalhighClaude Opus 4.7mediumvsDeepSeek V4 Pro 0423highDeepSeek V4.1 Flash 1017maxvsGLM 5.3 FlashX LegalhighGemini 4 ArgonlowvsGLM 5.3 FlashX LegalhighQwen3.7 PlusmediumvsGLM 5.3 FlashX LegalhighLing 3.1 FlashmediumvsGLM 5.3 FlashX LegalhighSeed-2.0-LitemediumvsGLM 5.3 FlashX LegalhighSeed-2.0-CodelowvsDeepSeek V4 Pro 0423highClaude Opus 4.8mediumvsGLM 5.3 FlashX LegalhighGPT-6 LunamediumvsGLM 5.3 FlashX LegalhighSeed-2.0-CodelowvsGLM 5.3 FlashX LegalhighSeed-2.0-LitemediumvsDeepSeek V4 Pro 0423high