- Peringkat
- #28
- Total token output
- 43,450
- Waktu respons (rata-rata)
- 13.24s
- Total Biaya
- $2.870
Claude Opus 5 (medium) vs Gemini 4 Argon (high)
Gemini 4 Argon (high) unggul dalam skor rata-rata dengan 9.5 vs 9.4. Gemini 4 Argon (high) memiliki biaya benchmark lebih rendah di $1.802 vs $2.870. Claude Opus 5 (medium) lebih cepat di 13.24s vs 19.03s, dengan tingkat keberhasilan 84.1% vs 97.1%.
Model yang Dibandingkan
- Peringkat
- #17
- Total token output
- 132,073
- Waktu respons (rata-rata)
- 19.03s
- Total Biaya
- $1.802
Model yang direkomendasikan
Gemini 4 Argon (high)
It has the best score here (9.5), while costing about 1.6x less than Claude Opus 5 (medium).
Perbandingan terperinci
| Metrik | Claude Opus 5 Claude Opus 5 medium | Gemini 4 Argon Gemini 4 Argon high |
|---|---|---|
| Skor | 9.4 | 9.5 |
| Peringkat | #28 | #17 |
| Keandalan | 10.0 | 9.9 |
| Konsistensi | 9.6 | 9.3 |
| Percobaan | 69/69 | 69/69 |
| Tes benar | ||
| Tingkat lulus per percobaan | 84.1% | 97.1% |
| Tes tidak stabil | 1 | 2 |
| Total Run | 69 | 69 |
| Biaya per hasil | 15.102 | 8.578 |
| Total Biaya | $2.870 | $1.802 |
| Harga input | $5.000 / 1M | $2.000 / 1M |
| Harga output | $25.000 / 1M | $10.000 / 1M |
| Harga baca cache | $0.500 / 1M | $0.100 / 1M |
| Harga tulis cache | $6.250 / 1M | $0.188 / 1M |
| Total token input | 356,605 | 240,264 |
| Token output | 26,715 | 5,707 |
| Token penalaran | 17,041 | 126,366 |
| Waktu respons (rata-rata) | 13.24s | 19.03s |
| Waktu respons (maks) | 78.80s | 82.53s |
| Waktu respons (total) | 304.46s | 437.77s |
| Parameter | ~5T total (~500B aktif) | ~1.2T 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.
#28 Claude Opus 5
medium- Biaya
- $0.125
- Waktu
- 69.3s
- Token
- 5,134 tok
#17 Gemini 4 Argon
high- Biaya
- $0.173
- Waktu
- 141.5s
- Token
- 17,366 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 Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 78.80s | 221,001 | 2,901 | 4,237 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 82.53s | 162,601 | 1,058 | 16,544 |
| 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 Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 5.46s | 834 | 1,559 | 572 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 3.98s | 918 | 155 | 3,556 |
| Pemrograman | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 9.56s | 10,590 | 5,224 | 1,162 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 15.81s | 8,448 | 489 | 20,751 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 23.89s | 98,197 | 7,895 | 1,276 | |
| Gemini 4 Argon | 7.3 | 5.8 | 83.3% | 1 | 56.32s | 50,219 | 2,878 | 32,994 |
| 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 Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 3.92s | 10,503 | 355 | 161 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 8.04s | 8,025 | 338 | 5,519 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 2.9 | 7.2 | 11.1% | 1 | 26.35s | 972 | 6,224 | 8,562 | |
| Gemini 4 Argon | 8.2 | 7.2 | 88.9% | 1 | 32.86s | 963 | 49 | 29,490 |
| Kecerdasan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 3.56s | 708 | 291 | 0 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 6.44s | 591 | 127 | 1,572 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 4.16s | 909 | 377 | 351 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 5.32s | 825 | 96 | 2,992 |
| 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 Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 4.27s | 894 | 836 | 465 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 4.46s | 882 | 220 | 2,859 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 8.76s | 11,739 | 354 | 0 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 28.47s | 6,531 | 273 | 8,505 |
| Pengetahuan umum | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token input | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 3.0 | 10.0 | 0.0% | 0 | 7.03s | 258 | 699 | 255 | |
| Gemini 4 Argon | 10.0 | 10.0 | 100.0% | 0 | 5.66s | 261 | 24 | 1,584 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 4 ArgonhighvsGPT-6.1 SollowClaude Opus 5mediumvsGemini 3.7 FlashlowGemini 4 ArgonhighvsGPT-6 AstralowGemini 4 ArgonhighvsGPT-6 SolmediumGemini 4 ArgonhighvsGPT-5.6 SolmediumGemini 4 ArgonhighvsGPT-5.6 SollowGemini 4 ArgonhighvsGPT-6 AstramediumGemini 4 ArgonhighvsGPT-5.5lowClaude Opus 5mediumvsSeed 2.1 TurbolowGemini 4 ArgonhighvsGPT-6.1 SolmediumClaude Opus 5mediumvsGPT-5.5lowClaude Opus 5.5lowvsGemini 4 Argonhigh