AI BENCHY Compare
Google: Gemini 2.5 Flash vs Inception: Mercury 2
Bandingkan:
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-05
| Metrik | Google: Gemini 2.5 Flash none Rilis: 2025-06-17 | Inception: Mercury 2 medium Rilis: 2026-02-24 |
|---|---|---|
| Peringkat | #37 | #35 |
| Skor Rata-rata | 52 | 54 |
| Konsistensi | 90 | 83 |
| Biaya per hasil | 0.185 | 0.622 |
| Total Biaya | $0.012 | $0.044 |
| Waktu respons (rata-rata) | 944ms | 2.47s |
| Waktu respons (maks) | 4.39s | 14.63s |
| Waktu respons (total) | 14.16s | 34.56s |
| Tes benar | ||
| Tingkat lulus per percobaan | 46.7% | 57.8% |
| Tes tidak stabil | 2 | 3 |
| Token output | 1,192 | 3,571 |
| Token penalaran | 0 | 45,379 |
Waktu respons (rata-rata)
Skor vs Total Biaya
Skor Rata-rata vs Waktu respons (rata-rata)
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 100 | 100 | 0.0% | 0 | 668ms | 99 | 0 | |
| Inception: Mercury 2 | 73 | 98 | 66.7% | 0 | 1.30s | 2,531 | 2,410 |
| Gabungan | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 100 | 100 | 0.0% | 0 | 4.39s | 366 | 0 | |
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 3.28s | 268 | 4,887 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 99 | 100 | 100.0% | 0 | 652ms | 279 | 0 | |
| Inception: Mercury 2 | 55 | 59 | 83.3% | 1 | 1.11s | 183 | 1,656 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 40 | 72 | 55.6% | 1 | 495ms | 12 | 0 | |
| Inception: Mercury 2 | 100 | 72 | 11.1% | 1 | 6.48s | 41 | 30,754 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 90 | 68 | 66.7% | 1 | 672ms | 70 | 0 | |
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 1.07s | 14 | 958 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 47 | 100 | 33.3% | 0 | 576ms | 132 | 0 | |
| Inception: Mercury 2 | 17 | 75 | 22.2% | 1 | 934ms | 354 | 2,758 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Waktu respons (rata-rata) | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 100 | 100 | 100.0% | 0 | 1.91s | 234 | 0 | |
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 1.89s | 180 | 1,956 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 2.5 Flashnonevsgpt-oss-120bmediumTersedia gratisDeepSeek V3.2nonevsMercury 2mediumMercury 2mediumvsQwen3.5-122B-A10BnoneMercury 2mediumvsGLM 5noneGemini 2.5 FlashnonevsMiniMax M2.5mediumGemini 2.5 FlashnonevsGPT-5 NanomediumMercury 2mediumvsQwen3.5-FlashnoneMercury 2mediumvsQwen3.5-27BnoneGemini 2.5 FlashnonevsQwen3.5-35B-A3BmediumMercury 2mediumvsQwen3.5-35B-A3BnoneMercury 2mediumvsGPT-5.4noneGemini 2.5 FlashnonevsGPT-5 Minimedium