- Peringkat
- #258
- Total token output
- 15,499
- Waktu respons (rata-rata)
- 7.28s
- Total Biaya
- $0.030
Gemma 4 31B vs GPT-5 Nano (medium)
GPT-5 Nano (medium) unggul dalam skor rata-rata dengan 5.7 vs 5.7. Gemma 4 31B memiliki biaya benchmark lebih rendah di $0.030 vs $0.139. Gemma 4 31B lebih cepat di 7.28s vs 56.55s, dengan tingkat keberhasilan 42.0% vs 53.6%.
Model yang Dibandingkan
- Peringkat
- #254
- Total token output
- 307,921
- Waktu respons (rata-rata)
- 56.55s
- Total Biaya
- $0.139
Model yang direkomendasikan
Gemma 4 31B
Its score stays close to the best score here (5.7 vs 5.7), while costing about 4.7x less than GPT-5 Nano (medium).
Perbandingan terperinci
| Metrik | Gemma 4 31B Gemma 4 31B none Tersedia gratis | GPT-5 Nano GPT-5 Nano medium |
|---|---|---|
| Skor | 5.7 | 5.7 |
| Peringkat | #258 | #254 |
| Keandalan | 10.0 | 10.0 |
| Konsistensi | 9.6 | 6.5 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 42.0% | 53.6% |
| Tes tidak stabil | 1 | 10 |
| Total Run | 69 | 69 |
| Biaya per hasil | 0.520 | 1.737 |
| Total Biaya | $0.030 | $0.139 |
| Harga input | $0.090 / 1M | $0.050 / 1M |
| Harga output | $0.340 / 1M | $0.400 / 1M |
| Total token input | 270,970 | 314,436 |
| Token output | 15,499 | 13,578 |
| Token penalaran | 0 | 294,343 |
| Waktu respons (rata-rata) | 7.28s | 56.55s |
| Waktu respons (maks) | 44.73s | 227.89s |
| Waktu respons (total) | 152.84s | 961.32s |
| Parameter | 30.7B | ~120B total (~5B aktif) |
| Ketersediaan | Sumber terbuka | Tertutup |
Showcase generasi model
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#258 Gemma 4 31B
none- Biaya
- $0.001
- Waktu
- 12.8s
- Token
- 795 tok
#254 GPT-5 Nano
medium- Biaya
- $0.006
- Waktu
- 108.5s
- Token
- 13,209 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 | 3.9 | 9.6 | 0.0% | 0 | 44.73s | 145,267 | 2,182 | 0 | |
| GPT-5 Nano | 4.7 | 3.1 | 33.3% | 1 | 94.09s | 219,492 | 1,541 | 23,943 |
| 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 | 6.5 | 10.0 | 50.0% | 0 | 1.85s | 852 | 45 | 0 | |
| GPT-5 Nano | 6.5 | 7.9 | 58.3% | 1 | 25.50s | 606 | 1,221 | 21,184 |
| 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 | 5.5 | 10.0 | 33.3% | 0 | 11.19s | 8,381 | 735 | 0 | |
| GPT-5 Nano | 7.0 | 7.7 | 55.6% | 1 | 41.62s | 7,305 | 740 | 41,152 |
| 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 | 3.8 | 5.8 | 33.3% | 1 | 29.95s | 104,817 | 11,910 | 0 | |
| GPT-5 Nano | 6.4 | 5.8 | 66.7% | 1 | 146.93s | 71,846 | 7,156 | 86,976 |
| 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 | 2.25s | 8,352 | 285 | 0 | |
| GPT-5 Nano | 3.7 | 1.7 | 50.0% | 2 | 21.42s | 7,140 | 453 | 10,560 |
| 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 | 10.0 | 33.3% | 0 | 3.65s | 878 | 27 | 0 | |
| GPT-5 Nano | 3.4 | 1.6 | 44.4% | 3 | 124.13s | 628 | 232 | 73,792 |
| 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 | 2.09s | 576 | 117 | 0 | |
| GPT-5 Nano | 4.1 | 10.0 | 0.0% | 0 | 17.51s | 477 | 202 | 4,608 |
| 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 | 6.5 | 10.0 | 50.0% | 0 | 2.84s | 795 | 78 | 0 | |
| GPT-5 Nano | 9.8 | 10.0 | 100.0% | 0 | 15.64s | 660 | 312 | 4,736 |
| 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 | 6.5 | 10.0 | 33.3% | 0 | 4.23s | 828 | 108 | 0 | |
| GPT-5 Nano | 5.3 | 7.2 | 44.4% | 1 | 20.63s | 642 | 929 | 14,272 |
| 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-5 Nano | 10.0 | 10.0 | 100.0% | 0 | 33.30s | 5,445 | 558 | 6,976 |
| 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 | 1.25s | 224 | 12 | 0 | |
| GPT-5 Nano | 3.0 | 10.0 | 0.0% | 0 | 20.13s | 195 | 234 | 6,144 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Trinity Large ThinkinghighvsGPT-5 NanomediumSeed 2.1 TurbononevsGPT-5 NanomediumDots 3 Note PreviewmediumTersedia gratisvsGemma 4 31BnoneTersedia gratisGemma 4 31BnoneTersedia gratisvsSpace Bunny AlphalowLing 3.0 FlashhighvsGPT-5 NanomediumDeepSeek V4.1 FlashnonevsGPT-5 NanomediumTrinity Large ThinkinghighvsGemma 4 31BnoneTersedia gratisGemma 4 31BnoneTersedia gratisvsRing 2.6 1tmediumGPT-5 NanomediumvsSpace Bunny AlphalowGemma 4 31BnoneTersedia gratisvsLing 3.0 FlashhighGPT-5 NanomediumvsSolar Pro 4noneGPT-5 NanomediumvsQwen3.7 Flashnone