AI BENCHY Compare
ByteDance Seed: Seed-2.0-Mini vs Google: Gemini 3.1 Flash Lite Preview
Bandingkan:
Benchmark dihasilkan dari suite pengujian AI BENCHY pada: 2026-03-03
| Metrik | ByteDance Seed: Seed-2.0-Mini medium Rilis: 2026-02-14 | Google: Gemini 3.1 Flash Lite Preview none Rilis: 2026-03-03 |
|---|---|---|
| Peringkat | #26 | #10 |
| Skor Rata-rata | 6.13 | 7.70 |
| Konsistensi | 8.91 | 9.54 |
| Biaya per hasil | 0.177 | 0.116 |
| Total Biaya | $0.013 | $0.011 |
| Tes benar | ||
| Tingkat lulus per percobaan | 59.5% | 69.1% |
| Tes tidak stabil | 2 | 1 |
| Token output | 1,353 | 4,307 |
| Token penalaran | 24,362 | 0 |
Skor vs Total Biaya
Rincian Kategori
| Trik anti-AI | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 7.00 | 9.99 | 66.7% | 0 | 354 | 9,352 | |
| Google: Gemini 3.1 Flash Lite Preview | 6.00 | 7.85 | 55.6% | 1 | 1,086 | 0 |
| Parsing dan ekstraksi data | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 9.88 | 10.00 | 100.0% | 0 | 246 | 2,743 | |
| Google: Gemini 3.1 Flash Lite Preview | 9.88 | 10.00 | 100.0% | 0 | 399 | 0 |
| Spesifik domain | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 1.00 | 10.00 | 0.0% | 0 | 0 | 0 | |
| Google: Gemini 3.1 Flash Lite Preview | 4.00 | 10.00 | 33.3% | 0 | 568 | 0 |
| Kepatuhan instruksi | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 8.00 | 9.99 | 50.0% | 0 | 69 | 2,050 | |
| Google: Gemini 3.1 Flash Lite Preview | 9.00 | 10.00 | 50.0% | 0 | 574 | 0 |
| Puzzle Solving | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 5.33 | 4.91 | 77.8% | 2 | 462 | 4,982 | |
| Google: Gemini 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 898 | 0 |
| Pemanggilan alat | Skor | Konsistensi | Tingkat lulus per percobaan | Tes tidak stabil | Tes benar | Token output | Token penalaran |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed-2.0-Mini | 10.00 | 10.00 | 100.0% | 0 | 222 | 5,235 | |
| Google: Gemini 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 782 | 0 |
Perbandingan Cepat
Ganti Pasangan Perbandingan
Seed-2.0-MinimediumvsGLM 5noneSeed-2.0-MinimediumvsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsSeed-2.0-MinimediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.3-CodexmediumClaude Sonnet 4.6mediumvsGemini 3.1 Flash Lite PreviewnoneGemini 3.1 Flash Lite PreviewnonevsGLM 5mediumGemini 3.1 Flash Lite PreviewnonevsStep 3.5 FlashmediumTersedia gratisDeepSeek V3.2mediumvsGemini 3.1 Flash Lite PreviewnoneGemini 3.1 Flash Lite PreviewnonevsGPT-5.2mediumSeed-2.0-MinimediumvsGemini 2.5 FlashnoneGemini 3.1 Flash Lite PreviewnonevsQwen3.5-27BmediumGemini 3.1 Flash Lite PreviewnonevsQwen3.5-122B-A10Bmedium