AI BENCHY Compare
Google: Gemini 3.1 Flash Lite Preview vs StepFun: Step 3.5 Flash
Bandingkan:
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-03
| Metrik | Google: Gemini 3.1 Flash Lite Preview none Rilis: 2026-03-03 | StepFun: Step 3.5 Flash medium Rilis: 2026-02-01 Tersedia gratis |
|---|---|---|
| Peringkat | #10 | #17 |
| Skor Rata-rata | 7.70 | 7.00 |
| Konsistensi | 9.54 | 8.32 |
| Biaya per hasil | 0.116 | 0.000 |
| Total Biaya | $0.011 | $0.000 |
| Tes benar | ||
| Tingkat lulus per percobaan | 69.1% | 73.8% |
| Tes tidak stabil | 1 | 3 |
| Token output | 4,307 | 60,502 |
| Token penalaran | 0 | 117,044 |
Skor vs Total Biaya
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 6.00 | 7.85 | 55.6% | 1 | 1,086 | 0 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 13,924 | 17,208 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 9.88 | 10.00 | 100.0% | 0 | 399 | 0 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 535 | 11,548 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 4.00 | 10.00 | 33.3% | 0 | 568 | 0 | |
| StepFun: Step 3.5 Flash | 4.00 | 7.21 | 44.4% | 1 | 40,942 | 74,237 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 9.00 | 10.00 | 50.0% | 0 | 574 | 0 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 2,121 | 3,274 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 898 | 0 | |
| StepFun: Step 3.5 Flash | 2.00 | 4.96 | 33.3% | 2 | 2,705 | 6,975 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| Google: Gemini 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 782 | 0 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 275 | 3,802 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Gemini 3 Flash PreviewnonevsStep 3.5 FlashmediumTersedia gratisGemini 3.1 Flash Lite PreviewnonevsGPT-5.3-CodexmediumClaude Sonnet 4.6mediumvsGemini 3.1 Flash Lite PreviewnoneGPT-5.3 ChatnonevsStep 3.5 FlashmediumTersedia gratisGemini 3.1 Flash Lite PreviewnonevsGLM 5mediumGPT-5.2 ChatnonevsStep 3.5 FlashmediumTersedia gratisClaude Sonnet 4.6nonevsStep 3.5 FlashmediumTersedia gratisQwen3.5 Plus 2026-02-15nonevsStep 3.5 FlashmediumTersedia gratisDeepSeek V3.2mediumvsGemini 3.1 Flash Lite PreviewnoneGemini 3.1 Flash Lite PreviewnonevsGPT-5.2mediumGemini 3.1 Flash Lite PreviewhighvsStep 3.5 FlashmediumTersedia gratisGemini 3.1 Flash Lite PreviewlowvsStep 3.5 FlashmediumTersedia gratis