AI BENCHY Compare
DeepSeek: DeepSeek V3.2 vs OpenAI: GPT-5 Nano
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | DeepSeek: DeepSeek V3.2 none Toleo: 2025-12-01 | OpenAI: GPT-5 Nano medium Toleo: 2025-08-07 |
|---|---|---|
| Nafasi | #30 | #24 |
| Wastani wa alama | 4.70 | 5.86 |
| Uthabiti | 8.19 | 6.60 |
| Gharama kwa matokeo | 0.132 | 0.519 |
| Jumla ya gharama | $0.007 | $0.037 |
| Majaribio sahihi | 5/14 | 7/14 |
| Kiwango cha kupita kwa kila jaribio | 47.6% | 69.1% |
| Majaribio yasiyo thabiti | 3 | 6 |
| Tokeni za matokeo | 4,869 | 3,700 |
| Tokeni za hoja | 0 | 85,184 |
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 | |
| OpenAI: GPT-5 Nano | 7.00 | 9.99 | 66.7% | 0 | 1,107 | 19,968 |
| 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 | |
| OpenAI: GPT-5 Nano | 5.50 | 5.81 | 83.3% | 1 | 426 | 8,576 |
| 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 | |
| OpenAI: GPT-5 Nano | 4.00 | 4.41 | 55.6% | 2 | 195 | 33,600 |
| 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 | |
| OpenAI: GPT-5 Nano | 7.00 | 6.41 | 83.3% | 1 | 360 | 4,032 |
| 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 | |
| OpenAI: GPT-5 Nano | 4.67 | 4.90 | 55.6% | 2 | 1,054 | 12,032 |
| 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 | |
| OpenAI: GPT-5 Nano | 10.00 | 10.00 | 100.0% | 0 | 558 | 6,976 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
GPT-5 NanomediumvsGLM 5noneGPT-5 NanomediumvsQwen3.5 Plus 2026-02-15noneClaude Sonnet 4.6nonevsGPT-5 NanomediumDeepSeek V3.2nonevsGLM 4.7 FlashmediumGPT-5 NanomediumvsQwen3.5-122B-A10BnoneDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsQwen3.5-FlashmediumGPT-5 NanomediumvsQwen3.5-27BnoneDeepSeek V3.2nonevsQwen3 Coder NextmediumGPT-5 NanomediumvsQwen3.5-35B-A3BnoneDeepSeek V3.2nonevsQwen3.5-35B-A3Bmedium