AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Google: Gemini 3 Flash Preview
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 medium Toleo: 2025-12-01 | Google: Gemini 3 Flash Preview low Toleo: 2025-12-17 |
|---|---|---|
| Nafasi | #12 | #6 |
| Wastani wa alama | 6.98 | 8.36 |
| Uthabiti | 8.75 | 9.40 |
| Gharama kwa matokeo | 0.193 | 0.602 |
| Jumla ya gharama | $0.018 | $0.067 |
| Majaribio sahihi | 9/14 | 11/14 |
| Kiwango cha kupita kwa kila jaribio | 71.4% | 81.0% |
| Majaribio yasiyo thabiti | 2 | 1 |
| Tokeni za matokeo | 6,753 | 1,170 |
| Tokeni za hoja | 30,427 | 18,372 |
Mgawanyo wa kategoria
| Mbinu za kupinga AI | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.86 | 66.7% | 0 | 1,171 | 4,893 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 275 | 2,476 |
| Uchanganuzi na uchimbaji wa data | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 9.88 | 10.00 | 100.0% | 0 | 207 | 7,693 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 305 | 3,004 |
| Mahususi kwa domeni | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 4.00 | 7.21 | 44.4% | 1 | 3,081 | 7,856 | |
| Google: Gemini 3 Flash Preview | 4.00 | 7.21 | 44.4% | 1 | 12 | 6,410 |
| Ufuataji wa maagizo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 9.84 | 50.0% | 0 | 1,397 | 2,845 | |
| Google: Gemini 3 Flash Preview | 7.50 | 9.99 | 50.0% | 0 | 71 | 2,752 |
| Puzzle Solving | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 7.00 | 7.21 | 88.9% | 1 | 390 | 6,281 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 273 | 3,315 |
| Mwito wa zana | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2 | 10.00 | 10.00 | 100.0% | 0 | 507 | 859 | |
| Google: Gemini 3 Flash Preview | 10.00 | 10.00 | 100.0% | 0 | 234 | 415 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Gemini 3 Flash PreviewlowvsQwen3.5-27BmediumDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneGemini 3 Flash PreviewlowvsQwen3.5 Plus 2026-02-15mediumGemini 3 Flash PreviewlowvsGPT-5.3-CodexmediumClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsGLM 5noneClaude Sonnet 4.6mediumvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsGLM 5mediumGemini 3 Flash PreviewlowvsStep 3.5 FlashmediumInapatikana bureGemini 3 Flash PreviewlowvsGPT-5.2mediumGemini 3 Flash PreviewlowvsQwen3.5-122B-A10Bmedium