AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 4.7 Flash
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 none Toleo: 2025-12-01 | Z.ai: GLM 4.7 Flash medium Toleo: 2026-01-19 |
|---|---|---|
| Nafasi | #30 | #34 |
| Wastani wa alama | 4.70 | 4.14 |
| Uthabiti | 8.19 | 6.42 |
| Gharama kwa matokeo | 0.132 | 0.227 |
| Jumla ya gharama | $0.007 | $0.012 |
| Majaribio sahihi | 5/14 | 5/14 |
| Kiwango cha kupita kwa kila jaribio | 47.6% | 52.4% |
| Majaribio yasiyo thabiti | 3 | 6 |
| Tokeni za matokeo | 4,869 | 8,003 |
| Tokeni za hoja | 0 | 22,680 |
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 | |
| Z.ai: GLM 4.7 Flash | 4.00 | 4.48 | 55.6% | 2 | 1,085 | 5,597 |
| 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 | |
| Z.ai: GLM 4.7 Flash | 10.00 | 10.00 | 100.0% | 0 | 1,073 | 4,920 |
| 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 | |
| Z.ai: GLM 4.7 Flash | 1.00 | 4.41 | 33.3% | 2 | 4,499 | 4,743 |
| 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 | |
| Z.ai: GLM 4.7 Flash | 5.00 | 5.81 | 66.7% | 1 | 380 | 2,141 |
| 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 | |
| Z.ai: GLM 4.7 Flash | 1.00 | 7.20 | 11.1% | 1 | 742 | 4,265 |
| 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 | |
| Z.ai: GLM 4.7 Flash | 10.00 | 10.00 | 100.0% | 0 | 224 | 1,014 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Kimi K2.5nonevsGLM 4.7 FlashmediumTrinity Large Preview (free)noneInapatikana burevsGLM 4.7 FlashmediumQwen3 Coder NextnonevsGLM 4.7 FlashmediumQwen3.5-35B-A3BnonevsGLM 4.7 FlashmediumQwen3.5-FlashnonevsGLM 4.7 FlashmediumQwen3.5-27BnonevsGLM 4.7 FlashmediumGPT-4o-mininonevsGLM 4.7 FlashmediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureQwen3.5-122B-A10BnonevsGLM 4.7 FlashmediumMiMo-V2-FlashnonevsGLM 4.7 FlashmediumDeepSeek V3.2nonevsQwen3.5-Flashmedium