- Peringkat
- #18
- Total token output
- 40,071
- Waktu respons (rata-rata)
- 13.59s
- Total Biaya
- $3.364
Claude Fable 5.1 (high) vs Qwen3.8 Max (medium)
Skor rata-rata hampir imbang di 9.0 vs 9.0. Qwen3.8 Max (medium) memiliki biaya benchmark lebih rendah di $0.771 vs $3.364. Claude Fable 5.1 (high) lebih cepat di 13.59s vs 23.34s, dengan tingkat keberhasilan 89.4% vs 80.3%.
- Peringkat
- #21
- Total token output
- 92,047
- Waktu respons (rata-rata)
- 23.34s
- Total Biaya
- $0.771
Model yang direkomendasikan
Qwen3.8 Max (medium)
It has the best score here (9.0), while costing about 4.4x less than Claude Fable 5.1 (high).
Perbandingan terperinci
| Metrik | Claude Fable 5.1 Claude Fable 5.1 high | Qwen3.8 Max Qwen3.8 Max medium |
|---|---|---|
| Skor | 9.0 | 9.0 |
| Peringkat | #18 | #21 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.6 | 9.7 |
| Percobaan | 66/66 | 66/66 |
| Tes benar | ||
| Tingkat lulus per percobaan | 89.4% | 80.3% |
| Tes tidak stabil | 1 | 1 |
| Total Run | 66 | 66 |
| Biaya per hasil | 17.701 | 4.532 |
| Total Biaya | $3.364 | $0.771 |
| Harga input | $10.000 / 1M | $2.000 / 1M |
| Harga output | $50.000 / 1M | $6.000 / 1M |
| Total token input | 135,958 | 109,055 |
| Token output | 7,930 | 6,566 |
| Token penalaran | 32,141 | 85,481 |
| Waktu respons (rata-rata) | 13.59s | 23.34s |
| Waktu respons (maks) | 40.17s | 126.60s |
| Waktu respons (total) | 298.90s | 513.47s |
| Parameter | ~9.5T total (~878B aktif) | 2.4T total (~100B aktif) |
| Ketersediaan | Tertutup | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#18 Claude Fable 5.1
high- Biaya
- $0.384
- Waktu
- 102.5s
- Token
- 7,824 tok
#21 Qwen3.8 Max
medium- Biaya
- $0.028
- Waktu
- 71.9s
- Token
- 4,750 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 5.90s | 858 | 287 | 790 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 4.17s | 672 | 312 | 2,075 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 8.4 | 7.4 | 88.9% | 1 | 13.91s | 10,608 | 520 | 6,503 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 41.35s | 7,893 | 430 | 23,804 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 34.59s | 98,419 | 5,484 | 5,373 | |
| Qwen3.8 Max | 8.7 | 6.9 | 83.3% | 1 | 91.25s | 81,584 | 4,526 | 30,688 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 6.30s | 10,515 | 312 | 403 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 8.72s | 7,782 | 270 | 2,519 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 7.7 | 10.0 | 66.7% | 0 | 24.34s | 990 | 63 | 12,436 | |
| Qwen3.8 Max | 3.0 | 10.0 | 0.0% | 0 | 41.77s | 780 | 62 | 20,803 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 5.40s | 714 | 291 | 0 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 6.41s | 516 | 168 | 700 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 5.60s | 921 | 97 | 263 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 3.49s | 699 | 102 | 914 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 6.11s | 912 | 506 | 558 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 4.93s | 696 | 401 | 1,575 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 10.0 | 10.0 | 100.0% | 0 | 13.30s | 11,757 | 354 | 118 | |
| Qwen3.8 Max | 10.0 | 10.0 | 100.0% | 0 | 7.83s | 8,229 | 267 | 636 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 3.0 | 10.0 | 0.0% | 0 | 30.58s | 264 | 16 | 5,697 | |
| Qwen3.8 Max | 3.0 | 10.0 | 0.0% | 0 | 11.49s | 204 | 28 | 1,767 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Claude Fable 5.1highvsGemini 3.5 FlashmediumClaude Fable 5.1highvsGPT-5.5mediumQwen3.8 MaxmediumvsGrok 4.5highClaude Fable 5.1highvsQwen3.7 MaxmediumClaude Fable 5.1highvsSeed 2.1 TurbolowClaude Fable 5.1highvsGPT-5.3-CodexmediumSeed 2.1 TurbohighvsQwen3.8 MaxmediumSeed 2.1 TurbolowvsQwen3.8 MaxmediumGemini 3.5 FlashlowvsQwen3.8 MaxmediumClaude Fable 5.1highvsGemini 3.7 FlashlowClaude Fable 5.1highvsGemini 3.5 FlashlowClaude Opus 5highvsQwen3.8 Maxmedium