- Peringkat
- #13
- Total token output
- 188,726
- Waktu respons (rata-rata)
- 33.44s
- Total Biaya
- $10.319
Claude Fable 5.2 (xhigh) vs Gemini 3 Flash Preview (medium)
Claude Fable 5.2 (xhigh) unggul dalam skor rata-rata dengan 9.6 vs 9.6. Gemini 3 Flash Preview (medium) memiliki biaya benchmark lebih rendah di $0.876 vs $10.319. Gemini 3 Flash Preview (medium) lebih cepat di 21.57s vs 33.44s, dengan tingkat keberhasilan 94.2% vs 94.2%.
Model yang Dibandingkan
- Peringkat
- #16
- Total token output
- 252,536
- Waktu respons (rata-rata)
- 21.57s
- Total Biaya
- $0.876
Model yang direkomendasikan
Gemini 3 Flash Preview (medium)
Its score stays close to the best score here (9.6 vs 9.6), while costing about 11.8x less than Claude Fable 5.2 (xhigh).
Perbandingan terperinci
| Metrik | Claude Fable 5.2 Claude Fable 5.2 xhigh | Gemini 3 Flash Preview Gemini 3 Flash Preview medium |
|---|---|---|
| Skor | 9.6 | 9.6 |
| Peringkat | #13 | #16 |
| Keandalan | 9.2 | 10.0 |
| Konsistensi | 9.6 | 9.7 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 94.2% | 94.2% |
| Tes tidak stabil | 1 | 1 |
| Total Run | 69 | 69 |
| Biaya per hasil | 49.137 | 4.169 |
| Total Biaya | $10.319 | $0.876 |
| Harga input | $8.000 / 1M | $0.500 / 1M |
| Harga output | $40.000 / 1M | $3.000 / 1M |
| Harga baca cache | $0.200 / 1M | $0.050 / 1M |
| Harga tulis cache | $10.000 / 1M | $0.084 / 1M |
| Total token input | 346,216 | 235,726 |
| Token output | 10,245 | 6,669 |
| Token penalaran | 178,481 | 245,867 |
| Waktu respons (rata-rata) | 33.44s | 21.57s |
| Waktu respons (maks) | 440.05s | 117.26s |
| Waktu respons (total) | 769.21s | 496.12s |
| Parameter | ~9.5T total (~878B aktif) | ~500B total (~20B aktif) |
| Ketersediaan | Tertutup | 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.
#13 Claude Fable 5.2
xhigh
Reached the allocated time limit (600 seconds) without receiving showcase output.
- Biaya
- $0.000
- Waktu
- 600.0s
- Token
- 0 tok
#16 Gemini 3 Flash Preview
medium- Biaya
- $0.010
- Waktu
- 18.4s
- Token
- 3,351 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 58.94s | 181,535 | 2,257 | 4,701 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 59.24s | 147,856 | 1,183 | 11,745 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 3.93s | 858 | 223 | 721 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.88s | 494 | 330 | 3,216 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 12.97s | 10,608 | 553 | 9,868 | |
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 10.0 | 10.0 | 100.0% | 0 | 45.25s | 122,664 | 5,583 | 21,413 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 26.75s | 63,717 | 3,831 | 23,496 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 6.79s | 10,515 | 312 | 1,320 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.43s | 7,548 | 279 | 4,893 |
| 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 5.2 | 7.7 | 10.0 | 66.7% | 0 | 164.07s | 990 | 53 | 134,111 | |
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 20.09s | 642 | 12 | 28,642 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 4.48s | 714 | 340 | 297 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.19s | 486 | 72 | 1,905 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 5.15s | 921 | 96 | 755 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 615 | 72 | 2,709 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 4.55s | 912 | 397 | 740 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.05s | 558 | 183 | 4,365 |
| 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 5.2 | 10.0 | 10.0 | 100.0% | 0 | 23.78s | 16,235 | 412 | 3,508 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 12.60s | 5,532 | 234 | 1,487 |
| 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 5.2 | 4.7 | 1.6 | 66.7% | 1 | 7.14s | 264 | 19 | 1,047 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.50s | 156 | 11 | 2,325 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Claude Fable 5.2xhighvsGPT-6.1 SolhighClaude Fable 5.2xhighvsGPT-6.1 SolmediumGemini 3 Flash PreviewmediumvsGPT-6.1 SollowGemini 3 Flash PreviewmediumvsGPT-6 AstralowClaude Fable 5.2xhighvsGPT-5.6 SollowGemini 3 Flash PreviewmediumvsGPT-5.6 SollowClaude Fable 5.2xhighvsGPT-6 AstralowGemini 3 Flash PreviewmediumvsGPT-6.1 SolhighGemini 3 Flash PreviewmediumvsGPT-6.1 TerrahighClaude Fable 5.2xhighvsGPT-6.1 SollowGemini 3 Flash PreviewmediumvsGPT-5.6 SolhighClaude Fable 5.2xhighvsGPT-6.1 Terramedium