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 none Toleo: 2025-12-17 |
|---|---|---|
| Nafasi | #12 | #10 |
| Wastani wa alama | 6.98 | 7.21 |
| Uthabiti | 8.75 | 9.36 |
| Gharama kwa matokeo | 0.193 | 0.078 |
| Jumla ya gharama | $0.018 | $0.007 |
| Majaribio sahihi | 9/14 | 9/13 |
| Kiwango cha kupita kwa kila jaribio | 71.4% | 71.8% |
| Majaribio yasiyo thabiti | 2 | 1 |
| Tokeni za matokeo | 6,753 | 734 |
| Tokeni za hoja | 30,427 | 0 |
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 | 7.00 | 10.00 | 66.7% | 0 | 240 | 0 |
| 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 | 9.88 | 10.00 | 100.0% | 0 | 279 | 0 |
| 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 | 7.00 | 10.00 | 66.7% | 0 | 18 | 0 |
| 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 | 5.50 | 5.81 | 66.7% | 1 | 74 | 0 |
| 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 | 7.00 | 10.00 | 66.7% | 0 | 123 | 0 |
| 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 | - | - | - | - | - | - | - |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Gemini 3 Flash PreviewnonevsGLM 5mediumGemini 3 Flash PreviewnonevsStep 3.5 FlashmediumInapatikana bureClaude Sonnet 4.6mediumvsGemini 3 Flash PreviewnoneGemini 3 Flash PreviewnonevsGPT-5.2mediumGemini 3 Flash PreviewnonevsQwen3.5-122B-A10BmediumClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneGemini 3 Flash PreviewnonevsGPT-5.3-CodexmediumDeepSeek V3.2mediumvsGLM 5noneGemini 3 Flash PreviewnonevsGrok 4.1 FastmediumGemini 3 Flash PreviewnonevsKimi K2.5mediumSeed-2.0-MinimediumvsGemini 3 Flash Previewnone