AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Google: Gemini 3.1 Pro 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 3.1 Pro Preview medium Toleo: 2026-02-19 |
|---|---|---|
| Nafasi | #12 | #2 |
| Wastani wa alama | 6.98 | 9.36 |
| Uthabiti | 8.75 | 10.00 |
| Gharama kwa matokeo | 0.193 | 2.443 |
| Jumla ya gharama | $0.018 | $0.318 |
| Majaribio sahihi | 9/14 | 13/14 |
| Kiwango cha kupita kwa kila jaribio | 71.4% | 92.9% |
| Majaribio yasiyo thabiti | 2 | 0 |
| Tokeni za matokeo | 6,753 | 1,000 |
| Tokeni za hoja | 30,427 | 22,936 |
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 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 106 | 2,533 |
| 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 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 292 | 3,164 |
| 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 3.1 Pro Preview | 7.00 | 10.00 | 66.7% | 0 | 18 | 10,688 |
| 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 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 72 | 2,436 |
| 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 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 238 | 3,133 |
| 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 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 274 | 982 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
DeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneClaude Sonnet 4.6nonevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsGLM 5noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewlowDeepSeek V3.2mediumvsQwen3.5-122B-A10BnoneDeepSeek V3.2mediumvsGPT-4o-mininoneDeepSeek V3.2mediumvsQwen3.5-27BnoneDeepSeek V3.2mediumvsQwen3.5-35B-A3BnoneTrinity Large Preview (free)noneInapatikana burevsDeepSeek V3.2mediumDeepSeek V3.2mediumvsKimi K2.5noneClaude Sonnet 4.6nonevsGemini 3.1 Pro Previewmedium