#47 Claude Opus 4.8
low- Biaya
- $0.031
- Waktu
- 14.1s
- Token
- 1,345 tok
AI BENCHY Compare
Anthropic: Claude Opus 4.8 vs StepFun: Step 3.7 Flash
Ringkasan
Skor rata-rata hampir imbang di 7.7 vs 7.7. Step 3.7 Flash (low) memiliki biaya benchmark lebih rendah di $0.341 vs $1.270. Claude Opus 4.8 (low) lebih cepat di 10.83s vs 15.74s, dengan tingkat keberhasilan 79.4% vs 68.3%.
Model yang direkomendasikanStep 3.7 Flash (low)It has the best score here (7.7), while costing about 3.7x less than Claude Opus 4.8 (low).
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-07-14
| Metrik | Claude Opus 4.8 Claude Opus 4.8 low | Step 3.7 Flash Step 3.7 Flash low |
|---|---|---|
| Skor | 7.7 | 7.7 |
| Peringkat | #47 | #51 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.8 | 8.4 |
| Tes benar | ||
| Tingkat lulus per percobaan | 79.4% | 68.3% |
| Tes tidak stabil | 3 | 4 |
| Total Run | 63 | 63 |
| Biaya per hasil | 8.466 | 2.840 |
| Total Biaya | $1.270 | $0.341 |
| Harga input | $5.000 / 1M | $0.200 / 1M |
| Harga output | $25.000 / 1M | $1.150 / 1M |
| Total token input | 60,946 | 40,101 |
| Token output | 31,771 | 289,325 |
| Token penalaran | 6,831 | 0 |
| Waktu respons (rata-rata) | 10.83s | 15.74s |
| Waktu respons (maks) | 127.97s | 124.75s |
| Waktu respons (total) | 227.39s | 330.63s |
Showcase generasi
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#51 Step 3.7 Flash
low
SVG tidak valid
- Biaya
- $0.004
- Waktu
- 25.3s
- Token
- 3,072 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
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 6.6 | 4.6 | 77.8% | 2 | 7.58s | 10,590 | 3,637 | 809 | |
| Step 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 9.46s | 7,437 | 18,685 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
GPT-5.6 LunahighvsStep 3.7 FlashlowClaude Opus 4.8lowvsQwen3.5-122B-A10BmediumClaude Opus 4.6mediumvsStep 3.7 FlashlowClaude Opus 4.8lowvsKimi K2.6mediumTersedia gratisStep 3.7 FlashlowvsGrok 4.3mediumClaude Opus 4.8lowvsGrok 4.3mediumClaude Opus 4.8lowvsGemini 3.1 Flash LitemediumKAT-Coder-Pro V2.5highvsStep 3.7 FlashlowClaude Opus 4.8lowvsQwen3.5 Plus 2026-04-20mediumClaude Opus 4.8lowvsGemini 3.1 Flash Lite PreviewmediumClaude Opus 4.8lowvsGPT-5.6 LunahighQwen3.5-122B-A10BmediumvsStep 3.7 Flashlow