#113 DeepSeek V4 Pro
none
Invalid SVG
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
AI BENCHY Compare
DeepSeek: DeepSeek V4 Pro vs Qwen: Qwen3 Coder Next
Ringkasan
Perbandingan benchmark DeepSeek V4 Pro vs Qwen3 Coder Next: DeepSeek V4 Pro unggul dalam skor rata-rata dengan 5.7 vs 4.6. Qwen3 Coder Next memiliki biaya benchmark lebih rendah di $0.008 vs $0.025. Qwen3 Coder Next lebih cepat di 8.58s vs 12.38s, dengan tingkat keberhasilan 42.9% vs 28.6%.
Model yang direkomendasikan: Qwen3 Coder Next - It offers the best overall trade-off: a competitive score (4.6), lower cost than DeepSeek V4 Pro, and balanced response time.
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-06-04
| Metrik | DeepSeek V4 Pro DeepSeek V4 Pro none | Qwen3 Coder Next Qwen3 Coder Next medium |
|---|---|---|
| Skor | 5.7 | 4.6 |
| Peringkat | #113 | #150 |
| Keandalan | 8.5 | 10.0 |
| Konsistensi | 8.5 | 8.9 |
| Tes benar | ||
| Tingkat lulus per percobaan | 42.9% | 28.6% |
| Tes tidak stabil | 4 | 3 |
| Total Run | 63 | 63 |
| Biaya per hasil | 0.660 | 0.201 |
| Total Biaya | $0.025 | $0.008 |
| Harga input | $0.435 / 1M | $0.110 / 1M |
| Harga output | $0.870 / 1M | $0.800 / 1M |
| Total token input | 44,845 | 47,250 |
| Token output | 5,349 | 3,319 |
| Token penalaran | 0 | 0 |
| Waktu respons (rata-rata) | 12.38s | 8.58s |
| Waktu respons (maks) | 58.65s | 81.80s |
| Waktu respons (total) | 260.06s | 128.68s |
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#150 Qwen3 Coder Next
medium
Invalid SVG
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 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 V4 Pro | 3.5 | 8.0 | 16.7% | 1 | 14.02s | 540 | 704 | 0 | |
| Qwen3 Coder Next | 3.5 | 8.1 | 16.7% | 1 | 8.64s | 645 | 1,252 | 0 |
| 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 | 4.6 | 7.9 | 22.2% | 1 | 6.11s | 7,279 | 531 | 0 | |
| Qwen3 Coder Next | 3.7 | 7.2 | 22.2% | 1 | 924ms | 7,185 | 336 | 0 |
| 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 | 9.5 | 10.0 | 100.0% | 0 | 25.49s | 20,773 | 1,911 | 0 | |
| Qwen3 Coder Next | 3.0 | 10.0 | 0.0% | 0 | 4.28s | 20,469 | 317 | 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 V4 Pro | 6.9 | 5.8 | 66.7% | 1 | 30.54s | 5,633 | 170 | 0 | |
| Qwen3 Coder Next | 6.5 | 10.0 | 50.0% | 0 | 81.80s | 7,758 | 246 | 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 V4 Pro | 5.3 | 10.0 | 33.3% | 0 | 3.17s | 666 | 18 | 0 | |
| Qwen3 Coder Next | 5.3 | 10.0 | 33.3% | 0 | 638ms | 753 | 25 | 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 V4 Pro | 4.3 | 9.9 | 0.0% | 0 | 3.75s | 471 | 132 | 0 | |
| Qwen3 Coder Next | 6.3 | 3.4 | 66.7% | 1 | 1.39s | 498 | 142 | 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 V4 Pro | 6.3 | 10.0 | 50.0% | 0 | 8.23s | 627 | 64 | 0 | |
| Qwen3 Coder Next | 6.3 | 10.0 | 50.0% | 0 | 7.49s | 684 | 63 | 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 V4 Pro | 7.6 | 7.2 | 77.8% | 1 | 15.95s | 594 | 173 | 0 | |
| Qwen3 Coder Next | 3.0 | 10.0 | 0.0% | 0 | 1.25s | 678 | 671 | 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 V4 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.92s | 8,079 | 219 | 0 | |
| Qwen3 Coder Next | 10.0 | 10.0 | 100.0% | 0 | 2.64s | 8,364 | 255 | 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 V4 Pro | 3.0 | 10.0 | 0.0% | 0 | 15.59s | 183 | 1,427 | 0 | |
| Qwen3 Coder Next | 3.0 | 10.0 | 0.0% | 0 | 399ms | 216 | 12 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Trinity Large PreviewnonevsQwen3 Coder NextmediumGPT-5.4 NanononevsQwen3 Coder NextmediumQwen3 Coder NextmediumvsMiMo-V2-FlashnoneCobuddymediumvsDeepSeek V4 PrononeDeepSeek V4 PrononevsNemotron 3 SupermediumTersedia gratisMercury 2nonevsQwen3 Coder NextmediumGPT-4o-mininonevsQwen3 Coder NextmediumGPT-5.4 MininonevsQwen3 Coder NextmediumQwen3 Coder NextmediumvsMiMo-V2.5noneMistral Small 4nonevsQwen3 Coder NextmediumNemotron 3 SupernoneTersedia gratisvsQwen3 Coder NextmediumDeepSeek V4 FlashnonevsQwen3 Coder Nextmedium