- Peringkat
- #20
- Total token output
- 74,662
- Waktu respons (rata-rata)
- 8.16s
- Total Biaya
- $0.278
Gemini 3.7 Flash (medium) vs GPT-6.1 Sol (high)
GPT-6.1 Sol (high) unggul dalam skor rata-rata dengan 9.6 vs 9.5. Gemini 3.7 Flash (medium) memiliki biaya benchmark lebih rendah di $0.278 vs $0.755. Gemini 3.7 Flash (medium) lebih cepat di 8.16s vs 15.46s, dengan tingkat keberhasilan 94.2% 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
Gemini 3.7 Flash (medium)
Its score stays close to the best score here (9.5 vs 9.6), while costing about 2.7x less than GPT-6.1 Sol (high).
Perbandingan terperinci
| Metrik | Gemini 3.7 Flash Gemini 3.7 Flash medium | GPT-6.1 Sol GPT-6.1 Sol high |
|---|---|---|
| Skor | 9.5 | 9.6 |
| Peringkat | #20 | #12 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.7 | 9.6 |
| 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 | 1.321 | 3.596 |
| Total Biaya | $0.278 | $0.755 |
| Harga input | $0.750 / 1M | $2.000 / 1M |
| Harga output | $3.750 / 1M | $10.000 / 1M |
| Harga baca cache | $0.075 / 1M | $0.100 / 1M |
| Harga tulis cache | $0.042 / 1M | $2.500 / 1M |
| Total token input | 202,347 | 174,960 |
| Token output | 6,660 | 5,780 |
| Token penalaran | 68,002 | 34,728 |
| Waktu respons (rata-rata) | 8.16s | 15.46s |
| Waktu respons (maks) | 58.39s | 139.76s |
| Waktu respons (total) | 187.58s | 355.66s |
| Parameter | ~500B total (~20B 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.
#20 Gemini 3.7 Flash
medium- Biaya
- $0.014
- Waktu
- 35.2s
- Token
- 7,283 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 58.39s | 113,292 | 963 | 9,122 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.17s | 492 | 153 | 2,985 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 8.4 | 7.4 | 88.9% | 1 | 8.86s | 8,118 | 450 | 16,777 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 20.93s | 64,983 | 4,254 | 19,096 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.33s | 7,548 | 279 | 2,725 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 7.7 | 10.0 | 66.7% | 0 | 6.49s | 642 | 12 | 8,262 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.45s | 486 | 80 | 1,317 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.81s | 615 | 72 | 2,410 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.33s | 558 | 161 | 2,279 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 5.83s | 5,457 | 225 | 1,305 | |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 156 | 11 | 1,724 | |
| 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 SolhighGemini 3.7 FlashmediumvsGPT-6.1 TerrahighGemini 3.7 FlashmediumvsGPT-5.6 SolhighGemini 3.7 FlashmediumvsGPT-6.1 SollowGemini 3.7 FlashmediumvsGPT-6 AstralowGemini 3.7 FlashmediumvsGPT-5.5lowGemini 3 Flash PreviewmediumvsGPT-6.1 SolhighClaude Opus 5.5lowvsGemini 3.7 FlashmediumGemini 3.7 FlashmediumvsGPT-5.6 SollowGemini 3.7 FlashmediumvsGPT-6.1 TerramaxClaude Opus 5.5highvsGemini 3.7 FlashmediumClaude Fable 5.2xhighvsGemini 3.7 Flashmedium