AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.5 Plus 2026-02-15
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 medium Toleo: 2025-12-01 | Qwen: Qwen3.5 Plus 2026-02-15 none Toleo: 2026-02-15 |
|---|---|---|
| Nafasi | #12 | #16 |
| Wastani wa alama | 6.98 | 6.29 |
| Uthabiti | 8.75 | 9.99 |
| Gharama kwa matokeo | 0.193 | 0.139 |
| Jumla ya gharama | $0.018 | $0.012 |
| Majaribio sahihi | 9/14 | 8/14 |
| Kiwango cha kupita kwa kila jaribio | 71.4% | 57.1% |
| Majaribio yasiyo thabiti | 2 | 0 |
| Tokeni za matokeo | 6,753 | 1,499 |
| 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 4.00 | 10.00 | 33.3% | 0 | 514 | 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 10.00 | 10.00 | 100.0% | 0 | 243 | 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 4.00 | 10.00 | 33.3% | 0 | 15 | 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 9.50 | 10.00 | 100.0% | 0 | 71 | 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 5.00 | 9.96 | 33.3% | 0 | 434 | 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 | |
| Qwen: Qwen3.5 Plus 2026-02-15 | 10.00 | 10.00 | 100.0% | 0 | 222 | 0 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Qwen3.5 Plus 2026-02-15nonevsGrok 4.1 FastmediumKimi K2.5mediumvsQwen3.5 Plus 2026-02-15noneSeed-2.0-MinimediumvsQwen3.5 Plus 2026-02-15noneClaude Opus 4.6mediumvsQwen3.5 Plus 2026-02-15noneDeepSeek V3.2mediumvsGemini 3 Flash PreviewnoneQwen3.5 Plus 2026-02-15nonevsMiMo-V2-FlashmediumGPT-5 NanomediumvsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsDeepSeek V3.2mediumgpt-oss-120bmediumInapatikana burevsQwen3.5 Plus 2026-02-15noneMiniMax M2.5mediumvsQwen3.5 Plus 2026-02-15noneGPT-5.2mediumvsQwen3.5 Plus 2026-02-15noneQwen3.5 Plus 2026-02-15nonevsStep 3.5 FlashmediumInapatikana bure