AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs MoonshotAI: Kimi K2.5
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 none Toleo: 2025-12-01 | MoonshotAI: Kimi K2.5 medium Toleo: 2026-01-27 |
|---|---|---|
| Nafasi | #30 | #18 |
| Wastani wa alama | 4.70 | 6.29 |
| Uthabiti | 8.19 | 7.69 |
| Gharama kwa matokeo | 0.132 | 2.335 |
| Jumla ya gharama | $0.007 | $0.187 |
| Majaribio sahihi | 5/14 | 8/14 |
| Kiwango cha kupita kwa kila jaribio | 47.6% | 73.8% |
| Majaribio yasiyo thabiti | 3 | 4 |
| Tokeni za matokeo | 4,869 | 30,504 |
| Tokeni za hoja | 0 | 58,467 |
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 | |
| MoonshotAI: Kimi K2.5 | 7.00 | 7.21 | 88.9% | 1 | 335 | 6,255 |
| 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 | |
| MoonshotAI: Kimi K2.5 | 10.00 | 10.00 | 100.0% | 0 | 1,181 | 6,049 |
| 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 | |
| MoonshotAI: Kimi K2.5 | 1.00 | 4.41 | 33.3% | 2 | 20,696 | 30,894 |
| 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 | |
| MoonshotAI: Kimi K2.5 | 9.50 | 10.00 | 100.0% | 0 | 3,777 | 4,967 |
| 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 | |
| MoonshotAI: Kimi K2.5 | 5.00 | 7.61 | 55.6% | 1 | 4,273 | 9,490 |
| 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 | |
| MoonshotAI: Kimi K2.5 | 10.00 | 10.00 | 100.0% | 0 | 242 | 812 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Kimi K2.5mediumvsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsKimi K2.5mediumKimi K2.5mediumvsGLM 5noneDeepSeek V3.2nonevsGLM 4.7 FlashmediumGemini 3 Flash PreviewnonevsKimi K2.5mediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsQwen3.5-FlashmediumKimi K2.5mediumvsQwen3.5-122B-A10BnoneDeepSeek V3.2nonevsGPT-5 NanomediumDeepSeek V3.2nonevsQwen3 Coder NextmediumDeepSeek V3.2nonevsQwen3.5-35B-A3Bmedium