- Peringkat
- #36
- Total token output
- 523,482
- Waktu respons (rata-rata)
- 32.55s
- Total Biaya
- $0.355
DeepSeek V4.1 Flash 1017 (low) vs Qwen3.8 Max (0902) (high)
Skor rata-rata hampir imbang di 9.2 vs 9.1. DeepSeek V4.1 Flash 1017 (low) memiliki biaya benchmark lebih rendah di $0.355 vs $3.306. DeepSeek V4.1 Flash 1017 (low) lebih cepat di 32.55s vs 186.06s, dengan tingkat keberhasilan 78.3% vs 87.0%.
Model yang Dibandingkan
- Peringkat
- #37
- Total token output
- 441,352
- Waktu respons (rata-rata)
- 186.06s
- Total Biaya
- $3.306
Model yang direkomendasikan
DeepSeek V4.1 Flash 1017 (low)
It has the best score here (9.2), while costing about 9.3x less than Qwen3.8 Max (0902) (high).
Perbandingan terperinci
| Metrik | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 low | Qwen3.8 Max (0902) Qwen3.8 Max (0902) high |
|---|---|---|
| Skor | 9.2 | 9.1 |
| Peringkat | #36 | #37 |
| Keandalan | 10.0 | 9.8 |
| Konsistensi | 9.0 | 9.1 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 78.3% | 87.0% |
| Tes tidak stabil | 3 | 3 |
| Total Run | 69 | 69 |
| Biaya per hasil | 2.214 | 18.364 |
| Total Biaya | $0.355 | $3.306 |
| Harga input | $0.150 / 1M | $2.000 / 1M |
| Harga output | $0.600 / 1M | $6.000 / 1M |
| Harga baca cache | $0.003 / 1M | $0.250 / 1M |
| Harga tulis cache | T/A | $2.500 / 1M |
| Total token input | 267,122 | 328,637 |
| Token output | 7,369 | 8,619 |
| Token penalaran | 516,113 | 432,733 |
| Waktu respons (rata-rata) | 32.55s | 186.06s |
| Waktu respons (maks) | 443.63s | 912.78s |
| Waktu respons (total) | 748.62s | 4279.49s |
| Parameter | ~748B total (~16B aktif) | 2.4T total (~100B 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.
#36 DeepSeek V4.1 Flash 1017
low- Biaya
- $0.006
- Waktu
- 63.8s
- Token
- 11,236 tok
#37 Qwen3.8 Max (0902)
high
Reached the allocated time limit (600 seconds) without receiving showcase output.
- Biaya
- $0.000
- Waktu
- 600.0s
- Token
- 0 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 V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 46.67s | 156,869 | 2,102 | 5,290 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 197.08s | 219,411 | 1,729 | 20,180 |
| 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 V4.1 Flash 1017 | 8.3 | 10.0 | 75.0% | 0 | 2.02s | 852 | 171 | 2,193 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 15.86s | 1,128 | 263 | 6,631 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 27.01s | 7,509 | 323 | 45,628 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 253.22s | 8,235 | 418 | 91,734 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 18.73s | 82,444 | 3,880 | 15,379 | |
| Qwen3.8 Max (0902) | 8.7 | 6.9 | 83.3% | 1 | 110.39s | 79,527 | 5,215 | 28,102 |
| 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 V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.71s | 7,446 | 207 | 1,344 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 16.37s | 8,010 | 261 | 3,598 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.6 | 7.2 | 22.2% | 1 | 174.63s | 909 | 9 | 428,331 | |
| Qwen3.8 Max (0902) | 5.9 | 7.2 | 55.6% | 1 | 658.46s | 842 | 31 | 154,450 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.25s | 549 | 116 | 553 | |
| Qwen3.8 Max (0902) | 6.5 | 3.4 | 66.7% | 1 | 75.11s | 630 | 80 | 8,110 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.25s | 783 | 69 | 898 | |
| Qwen3.8 Max (0902) | 9.8 | 10.0 | 100.0% | 0 | 7.55s | 927 | 86 | 1,823 |
| 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 V4.1 Flash 1017 | 6.9 | 4.9 | 77.8% | 2 | 2.54s | 828 | 236 | 3,620 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 134.14s | 1,038 | 268 | 47,351 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.92s | 8,672 | 237 | 338 | |
| Qwen3.8 Max (0902) | 10.0 | 10.0 | 100.0% | 0 | 5.21s | 8,571 | 249 | 243 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.0 | 10.0 | 0.0% | 0 | 33.79s | 261 | 19 | 12,539 | |
| Qwen3.8 Max (0902) | 3.0 | 10.0 | 0.0% | 0 | 532.59s | 318 | 19 | 70,511 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
GPT-5.3-CodexmediumvsQwen3.8 Max (0902)highClaude Haiku 5.5xhighvsQwen3.8 Max (0902)highDeepSeek V4.1 Flash 1017lowvsQwen3.8 MAXmediumClaude Sonnet 5.5maxvsDeepSeek V4.1 Flash 1017lowDeepSeek V4.1 Flash 1017lowvsGPT-5.5mediumMuse WonderlowvsQwen3.8 Max (0902)highDeepSeek V4.1 Flash 1017lowvsMuse WondermediumQwen3.8 Max (0902)highvsParetodefaultClaude Opus 5.5mediumvsDeepSeek V4.1 Flash 1017lowDeepSeek V4.1 Flash 1017lowvsGPT-5.3-CodexmediumDeepSeek V4.1 Flash 1017lowvsMuse Spark OpenhighClaude Haiku 5.5xhighvsDeepSeek V4.1 Flash 1017low