- Peringkat
- #164
- Total token output
- 277,315
- Waktu respons (rata-rata)
- 78.76s
- Total Biaya
- $0.117
Gemma 4 31B (medium) vs GPT-6 Sol
Gemma 4 31B (medium) unggul dalam skor rata-rata dengan 6.9 vs 6.8. Gemma 4 31B (medium) memiliki biaya benchmark lebih rendah di $0.117 vs $0.551. GPT-6 Sol lebih cepat di 9.02s vs 78.76s, dengan tingkat keberhasilan 66.7% vs 63.8%.
Model yang Dibandingkan
- Peringkat
- #172
- Total token output
- 7,989
- Waktu respons (rata-rata)
- 9.02s
- Total Biaya
- $0.551
Model yang direkomendasikan
Gemma 4 31B (medium)
It has the best score here (6.9), while costing about 4.7x less than GPT-6 Sol.
Perbandingan terperinci
| Metrik | Gemma 4 31B Gemma 4 31B medium Tersedia gratis | GPT-6 Sol GPT-6 Sol none |
|---|---|---|
| Skor | 6.9 | 6.8 |
| Peringkat | #164 | #172 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 8.7 | 8.5 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 66.7% | 63.8% |
| Tes tidak stabil | 3 | 4 |
| Total Run | 69 | 69 |
| Biaya per hasil | 1.195 | 4.232 |
| Total Biaya | $0.117 | $0.551 |
| Harga input | $0.090 / 1M | $2.000 / 1M |
| Harga output | $0.340 / 1M | $10.000 / 1M |
| Total token input | 251,164 | 235,086 |
| Token output | 36,112 | 7,989 |
| Token penalaran | 241,203 | 0 |
| Waktu respons (rata-rata) | 78.76s | 9.02s |
| Waktu respons (maks) | 437.40s | 57.02s |
| Waktu respons (total) | 1653.96s | 207.45s |
| Parameter | 30.7B | ~2T total (~150B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#164 Gemma 4 31B
medium- Biaya
- $0.002
- Waktu
- 45.7s
- Token
- 2,696 tok
#172 GPT-6 Sol
none- Biaya
- $0.030
- Waktu
- 31.9s
- Token
- 3,055 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
| Tugas agen | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 10.0 | 10.0 | 100.0% | 0 | 82.13s | 156,195 | 1,713 | 8,181 | |
| GPT-6 Sol | 5.0 | 10.0 | 0.0% | 0 | 57.02s | 128,754 | 1,293 | 0 |
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 10.0 | 10.0 | 100.0% | 0 | 12.89s | 816 | 962 | 2,046 | |
| GPT-6 Sol | 6.9 | 5.8 | 75.0% | 2 | 1.23s | 606 | 141 | 0 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 4.3 | 5.8 | 22.2% | 1 | 219.76s | 5,568 | 11,098 | 33,212 | |
| GPT-6 Sol | 5.5 | 10.0 | 33.3% | 0 | 12.23s | 7,302 | 389 | 0 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 2.9 | 5.8 | 16.7% | 1 | 433.11s | 77,035 | 12,112 | 157,552 | |
| GPT-6 Sol | 6.5 | 10.0 | 50.0% | 0 | 10.61s | 83,124 | 5,296 | 0 |
| 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 10.0 | 10.0 | 100.0% | 0 | 21.11s | 8,334 | 1,822 | 2,951 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 20.98s | 7,140 | 222 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 5.3 | 7.2 | 44.4% | 1 | 59.92s | 853 | 4,280 | 18,729 | |
| GPT-6 Sol | 5.3 | 7.2 | 44.4% | 1 | 3.41s | 732 | 52 | 0 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 10.0 | 10.0 | 100.0% | 0 | 9.57s | 567 | 105 | 888 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 23.89s | 477 | 81 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 10.0 | 10.0 | 100.0% | 0 | 12.76s | 777 | 533 | 2,035 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 1.23s | 660 | 81 | 0 |
| Pemecahan teka-teki | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 9.9 | 10.0 | 100.0% | 0 | 26.91s | 801 | 1,795 | 5,595 | |
| GPT-6 Sol | 7.6 | 7.2 | 77.8% | 1 | 1.40s | 642 | 187 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 3.0 | 10.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 3.43s | 5,454 | 226 | 0 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Gemma 4 31B | 3.0 | 10.0 | 0.0% | 0 | 90.14s | 218 | 1,692 | 10,014 | |
| GPT-6 Sol | 3.0 | 10.0 | 0.0% | 0 | 1.45s | 195 | 21 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemma 4 31BmediumTersedia gratisvsGPT-5.6 LunalowClaude Sonnet 5.5lowvsGemma 4 31BmediumTersedia gratisClaude Opus 4.8nonevsGemma 4 31BmediumTersedia gratisEmber-1highvsGemma 4 31BmediumTersedia gratisMercury 2.5 PreviewmediumvsGPT-6 SolnoneGPT-6 SolnonevsInklinglowTersedia gratisGPT-6 SolnonevsQwen3.5-FlashmediumKimi K2.6mediumvsGPT-6 SolnoneGemma 4 31BmediumTersedia gratisvsInklinglowTersedia gratisGPT-6 SolnonevsSpace Bunny AlphamaxClaude Sonnet 5.5lowvsGPT-6 SolnoneGPT-6 SolnonevsSolar Pro 4xhigh