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 none Toleo: 2025-12-01 | Google: Gemini 3.1 Pro Preview medium Toleo: 2026-02-19 |
|---|---|---|
| Nafasi | #30 | #2 |
| Wastani wa alama | 4.70 | 9.36 |
| Uthabiti | 8.19 | 10.00 |
| Gharama kwa matokeo | 0.132 | 2.443 |
| Jumla ya gharama | $0.007 | $0.318 |
| Majaribio sahihi | 5/14 | 13/14 |
| Kiwango cha kupita kwa kila jaribio | 47.6% | 92.9% |
| Majaribio yasiyo thabiti | 3 | 0 |
| Tokeni za matokeo | 4,869 | 1,000 |
| Tokeni za hoja | 0 | 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 | 1.00 | 9.68 | 0.0% | 0 | 1,411 | 0 | |
| 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 | 5.38 | 5.81 | 66.7% | 1 | 1,710 | 0 | |
| 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 | 1.00 | 7.21 | 22.2% | 1 | 24 | 0 | |
| 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 | 8.00 | 9.99 | 50.0% | 0 | 66 | 0 | |
| 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 | 7.67 | 7.49 | 88.9% | 1 | 1,136 | 0 | |
| 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 | 522 | 0 | |
| Google: Gemini 3.1 Pro Preview | 10.00 | 10.00 | 100.0% | 0 | 274 | 982 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
DeepSeek V3.2nonevsGLM 4.7 FlashmediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsQwen3.5-FlashmediumDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3 Coder NextmediumDeepSeek V3.2nonevsQwen3.5-35B-A3BmediumDeepSeek V3.2nonevsMiMo-V2-FlashmediumClaude Opus 4.6mediumvsDeepSeek V3.2noneSeed-2.0-MinimediumvsDeepSeek V3.2noneDeepSeek V3.2nonevsKimi K2.5mediumDeepSeek V3.2nonevsGrok 4.1 Fastmedium