- Peringkat
- #14
- Total token output
- 22,557
- Waktu respons (rata-rata)
- 11.13s
- Total Biaya
- $1.244
GPT-5.6 Sol (low) vs GPT-6.1 Sol (high)
Skor rata-rata hampir imbang di 9.6 vs 9.6. GPT-6.1 Sol (high) memiliki biaya benchmark lebih rendah di $0.755 vs $1.244. GPT-5.6 Sol (low) lebih cepat di 11.13s vs 15.46s, dengan tingkat keberhasilan 87.0% vs 94.2%.
Model yang Dibandingkan
- Peringkat
- #12
- Total token output
- 40,508
- Waktu respons (rata-rata)
- 15.46s
- Total Biaya
- $0.755
Model yang direkomendasikan
GPT-6.1 Sol (high)
It has the best score here (9.6), while costing about 1.6x less than GPT-5.6 Sol (low).
Perbandingan terperinci
| Metrik | GPT-5.6 Sol GPT-5.6 Sol low | GPT-6.1 Sol GPT-6.1 Sol high |
|---|---|---|
| Skor | 9.6 | 9.6 |
| Peringkat | #14 | #12 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.3 | 9.6 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 87.0% | 94.2% |
| Tes tidak stabil | 2 | 1 |
| Total Run | 69 | 69 |
| Biaya per hasil | 6.545 | 3.596 |
| Total Biaya | $1.244 | $0.755 |
| Harga input | $2.000 / 1M | $2.000 / 1M |
| Harga output | $10.000 / 1M | $10.000 / 1M |
| Harga baca cache | $0.200 / 1M | $0.100 / 1M |
| Harga tulis cache | $2.500 / 1M | $2.500 / 1M |
| Total token input | 191,653 | 174,960 |
| Token output | 5,473 | 5,780 |
| Token penalaran | 17,084 | 34,728 |
| Waktu respons (rata-rata) | 11.13s | 15.46s |
| Waktu respons (maks) | 57.11s | 139.76s |
| Waktu respons (total) | 256.08s | 355.66s |
| Parameter | ~2T total (~150B aktif) | ~2T total (~150B 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.
#14 GPT-5.6 Sol
low- Biaya
- $0.062
- Waktu
- 26.7s
- Token
- 2,150 tok
#12 GPT-6.1 Sol
high- Biaya
- $0.079
- Waktu
- 149.5s
- Token
- 7,920 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 |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 57.11s | 113,073 | 997 | 1,614 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 54.63s | 95,468 | 826 | 1,424 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 8.3 | 10.0 | 75.0% | 0 | 2.60s | 606 | 174 | 492 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.31s | 606 | 174 | 606 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 11.25s | 7,302 | 412 | 3,482 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 5.18s | 7,302 | 390 | 2,215 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 14.58s | 55,372 | 2,896 | 1,539 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 24.65s | 56,284 | 3,374 | 4,032 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 1.82s | 7,140 | 222 | 0 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 7,140 | 234 | 178 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 5.3 | 7.2 | 44.4% | 1 | 30.95s | 732 | 71 | 8,522 | |
| GPT-6.1 Sol | 7.7 | 10.0 | 66.7% | 0 | 59.04s | 732 | 68 | 23,791 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.07s | 477 | 99 | 135 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 5.90s | 477 | 112 | 449 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 2.27s | 660 | 90 | 146 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.63s | 660 | 93 | 500 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 8.2 | 7.2 | 88.9% | 1 | 3.44s | 642 | 224 | 534 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.99s | 642 | 223 | 633 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 7.56s | 5,454 | 258 | 294 | |
| GPT-6.1 Sol | 10.0 | 10.0 | 100.0% | 0 | 7.83s | 5,454 | 256 | 209 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.67s | 195 | 30 | 326 | |
| GPT-6.1 Sol | 4.7 | 1.6 | 66.7% | 1 | 7.29s | 195 | 30 | 691 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Claude Fable 5.2xhighvsGPT-6.1 SolhighClaude Fable 5.2xhighvsGPT-5.6 SollowGemini 3 Flash PreviewmediumvsGPT-5.6 SollowGemini 3 Flash PreviewmediumvsGPT-6.1 SolhighGemini 4 ArgonhighvsGPT-5.6 SollowGemini 3.7 FlashmediumvsGPT-5.6 SollowGemini 3.7 FlashmediumvsGPT-6.1 SolhighGemini 3.6 FlashmediumvsGPT-6.1 SolhighGemini 3.6 FlashmediumvsGPT-5.6 SollowGemini 3.7 FlashhighvsGPT-5.6 SollowClaude Opus 5.5lowvsGPT-6.1 SolhighClaude Opus 5.5highvsGPT-5.6 Sollow