AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Qwen: Qwen3.5-Flash
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 none Toleo: 2025-12-01 | Qwen: Qwen3.5-Flash medium Toleo: 2026-02-24 |
|---|---|---|
| Nafasi | #30 | #25 |
| Wastani wa alama | 4.70 | 5.79 |
| Uthabiti | 8.19 | 7.60 |
| Gharama kwa matokeo | 0.132 | 0.650 |
| Jumla ya gharama | $0.007 | $0.046 |
| Majaribio sahihi | 5/14 | 7/14 |
| Kiwango cha kupita kwa kila jaribio | 47.6% | 66.7% |
| Majaribio yasiyo thabiti | 3 | 4 |
| Tokeni za matokeo | 4,869 | 1,194 |
| Tokeni za hoja | 0 | 108,368 |
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 | |
| Qwen: Qwen3.5-Flash | 10.00 | 10.00 | 100.0% | 0 | 363 | 23,645 |
| 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 | |
| Qwen: Qwen3.5-Flash | 5.50 | 5.87 | 83.3% | 1 | 235 | 16,237 |
| 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 | |
| Qwen: Qwen3.5-Flash | 1.00 | 4.41 | 33.3% | 2 | 52 | 34,605 |
| 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 | |
| Qwen: Qwen3.5-Flash | 7.50 | 9.91 | 50.0% | 0 | 98 | 14,139 |
| 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 | |
| Qwen: Qwen3.5-Flash | 4.00 | 7.21 | 55.6% | 1 | 137 | 18,458 |
| 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 | |
| Qwen: Qwen3.5-Flash | 10.00 | 10.00 | 100.0% | 0 | 309 | 1,284 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Qwen3.5-FlashmediumvsGLM 5noneDeepSeek V3.2nonevsGLM 4.7 FlashmediumClaude Sonnet 4.6nonevsQwen3.5-FlashmediumGPT-4o-mininonevsQwen3.5-FlashmediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3 Coder NextmediumDeepSeek V3.2nonevsQwen3.5-35B-A3BmediumDeepSeek V3.2nonevsMiMo-V2-FlashmediumClaude Opus 4.6mediumvsDeepSeek V3.2noneGemini 3 Flash PreviewnonevsQwen3.5-Flashmedium