개인 의사결정EP3
🏠부동산
Real estate
내용 — 측정하는 AI 능력
- · 시세·입지 추론
- · 한국 부동산 법규 (DSR·전세보증·재건축·임대사업자)
- · 부동산 세제 (종합부동산세·장특공·취득세)
채점자 editor · max_tokens 32768 · temp 0.7 · attempts 3 · reasoning_effort medium
| 모델 | | | | | | | |
|---|
| 5/5 | 93 | 93 | 93 | 95 | 93 | 94.0 |
| 5/5 | 90 | 92 | 89 | 92 | 92 | 90.6 |
3Gemini 3.5 Flash | 5/5 | 89 | 90 | 87 | 93 | 89 | 90.0 |
4Gemini 3.1 Pro | 5/5 | 88 | 90 | 88 | 92 | 86 | 89.0 |
| 5/5 | 86 | 91 | 89 | 88 | 91 | 88.8 |
| 5/5 | 86 | 90 | 87 | 88 | 86 | 87.2 |
| 5/5 | 84 | 88 | 85 | 85 | 84 | 85.2 |
| 5/5 | 82 | 86 | 86 | 82 | 83 | 83.2 |
9Gemma 4 31B | 5/5 | 81 | 85 | 82 | 83 | 83 | 82.8 |
10Gemma 4 12B | 5/5 | 82 | 83 | 84 | 82 | 83 | 82.6 |
| 5/5 | 80 | 85 | 81 | 81 | 87 | 82.4 |
| 5/5 | 81 | 84 | 82 | 82 | 81 | 82.0 |
13Gemma 4 26B A4B | 5/5 | 78 | 82 | 80 | 81 | 81 | 80.4 |
14Gemini 3.1 Flash Lite | 5/5 | 77 | 82 | 80 | 81 | 78 | 79.6 |
| 5/5 | 78 | 81 | 82 | 72 | 83 | 78.2 |
| 5/5 | 71 | 81 | 74 | 71 | 83 | 75.0 |
17Nemotron 3 Ultra 550B | 5/5 | 69 | 84 | 80 | 65 | 88 | 75.0 |
| 5/5 | 66 | 85 | 86 | 59 | 91 | 74.8 |
19DeepSeek V4 Flash | 5/5 | 65 | 74 | 69 | 64 | 78 | 68.4 |
| 5/5 | 64 | 75 | 69 | 64 | 76 | 68.4 |
| 5/5 | 56 | 87 | 66 | 54 | 88 | 66.8 |
| 5/5 | 54 | 77 | 80 | 50 | 87 | 66.6 |
| 5/5 | 55 | 70 | 56 | 51 | 77 | 59.2 |
| 5/5 | 55 | 68 | 57 | 50 | 74 | 58.8 |
25HyperCLOVAX SEED Think 32B | 5/5 | 48 | 72 | 52 | 48 | 80 | 57.2 |
| 5/5 | 46 | 71 | 63 | 42 | 74 | 56.0 |
27Kanana 2 30B-A3B Thinking | 5/5 | 39 | 57 | 46 | 38 | 60 | 45.8 |
28Gemma 4 E2B | 5/5 | 38 | 49 | 36 | 34 | 47 | 39.6 |
| 5/5 | 28 | 49 | 39 | 26 | 53 | 36.4 |
30Mistral Small 4 | 5/5 | 25 | 49 | 34 | 25 | 55 | 35.0 |
31HyperCLOVAX SEED 1.5B | 5/5 | 26 | 40 | 25 | 23 | 38 | 29.0 |
| 5/5 | 24 | 39 | 23 | 20 | 39 | 26.8 |
GPT-5.5OpenAI
929292959293
Claude Sonnet 4.6Anthropic
859085859287
Gemini 3.5 FlashGoogle
909085958890
Gemini 3.1 ProGoogle
889085928588
Claude Opus 4.8Anthropic
809088829085
Qwen 3.7 MaxAlibaba
889290928890
DeepSeek V4 ProDeepSeek
858885888586
GPT-5.4 MiniOpenAI
788585788281
Gemma 4 31BGoogle
828582828282
Gemma 4 12BGoogle
808084768280
Mimo V2.5 ProXiaomi
828882859085
Gemma 4 26B A4BGoogle
788280808080
Gemini 3.1 Flash LiteGoogle
758280827880
Qwen 3.7 PlusAlibaba
788082728478
Kimi K2.6Moonshot
788582788881
Nemotron 3 Ultra 550BNVIDIA
587880588870
MiniMax M3Minimax
808588659280
DeepSeek V4 FlashDeepSeek
708075687873
Step 3.7 FlashStepFun
608878588871
Qwen 3.6 27BAlibaba
508080409064
EXAONE 4.5 33BLG AI
506550507556
Solar Pro 3Upstage
587058508061
HyperCLOVAX SEED Think 32BNaver
406060408053
Qwen 3.5 9BAlibaba
627572558066
Kanana 2 30B-A3B ThinkingKakao
101520151014
Gemma 4 E2BGoogle
415139374942
Qwen 3.6 35B A3BAlibaba
306055357047
Mistral Small 4Mistral
305540355541
HyperCLOVAX SEED 1.5BNaver
304328283932
LFM2.5 8B-A1BLiquid AI
254123214128
GPT-5.5OpenAI
929292959293
Claude Sonnet 4.6Anthropic
889288889289
Gemini 3.5 FlashGoogle
889085928889
Gemini 3.1 ProGoogle
889088928589
Claude Opus 4.8Anthropic
909390949292
Qwen 3.7 MaxAlibaba
859088908588
DeepSeek V4 ProDeepSeek
828582838283
GPT-5.4 MiniOpenAI
788282788080
Gemma 4 31BGoogle
808380828382
Gemma 4 12BGoogle
828684828483
Mimo V2.5 ProXiaomi
889088909290
Gemma 4 26B A4BGoogle
768078788078
Gemini 3.1 Flash LiteGoogle
728075757876
Qwen 3.7 PlusAlibaba
808584708479
Kimi K2.6Moonshot
587560608065
Nemotron 3 Ultra 550BNVIDIA
788882708879
MiniMax M3Minimax
709290709281
DeepSeek V4 FlashDeepSeek
556560587261
Step 3.7 FlashStepFun
659078629074
Qwen 3.6 27BAlibaba
558580508568
EXAONE 4.5 33BLG AI
657565608067
Solar Pro 3Upstage
607262558064
HyperCLOVAX SEED Think 32BNaver
408040408052
Qwen 3.5 9BAlibaba
457262407055
Kanana 2 30B-A3B ThinkingKakao
557060507560
Gemma 4 E2BGoogle
415139374942
Qwen 3.6 35B A3BAlibaba
101515101512
Mistral Small 4Mistral
285035305537
HyperCLOVAX SEED 1.5BNaver
233823193726
LFM2.5 8B-A1BLiquid AI
193419133622
GPT-5.5OpenAI
949494959494
Claude Sonnet 4.6Anthropic
929290959292
Gemini 3.5 FlashGoogle
909088959291
Gemini 3.1 ProGoogle
909290958892
Claude Opus 4.8Anthropic
859088889088
Qwen 3.7 MaxAlibaba
858888888587
DeepSeek V4 ProDeepSeek
808582788281
GPT-5.4 MiniOpenAI
858888858586
Gemma 4 31BGoogle
808582828282
Gemma 4 12BGoogle
848282868484
Mimo V2.5 ProXiaomi
889088929290
Gemma 4 26B A4BGoogle
788280828080
Gemini 3.1 Flash LiteGoogle
788280827880
Qwen 3.7 PlusAlibaba
788080687876
Kimi K2.6Moonshot
728075708275
Nemotron 3 Ultra 550BNVIDIA
788580688878
MiniMax M3Minimax
658285509071
DeepSeek V4 FlashDeepSeek
707875707873
Step 3.7 FlashStepFun
588865588868
Qwen 3.6 27BAlibaba
507580508565
EXAONE 4.5 33BLG AI
557055507859
Solar Pro 3Upstage
587258528062
HyperCLOVAX SEED Think 32BNaver
608060608066
Qwen 3.5 9BAlibaba
427065387554
Kanana 2 30B-A3B ThinkingKakao
406548357249
Gemma 4 E2BGoogle
435341395144
Qwen 3.6 35B A3BAlibaba
355545306243
Mistral Small 4Mistral
255035255836
HyperCLOVAX SEED 1.5BNaver
304328283932
LFM2.5 8B-A1BLiquid AI
233921183926
GPT-5.5OpenAI
949494969495
Claude Sonnet 4.6Anthropic
929290959292
Gemini 3.5 FlashGoogle
889088928890
Gemini 3.1 ProGoogle
889088908588
Claude Opus 4.8Anthropic
849088859087
Qwen 3.7 MaxAlibaba
889088908588
DeepSeek V4 ProDeepSeek
858885858585
GPT-5.4 MiniOpenAI
828585828283
Gemma 4 31BGoogle
808582858283
Gemma 4 12BGoogle
828484828483
Mimo V2.5 ProXiaomi
758078758277
Gemma 4 26B A4BGoogle
788280828281
Gemini 3.1 Flash LiteGoogle
808382828081
Qwen 3.7 PlusAlibaba
787682748278
Kimi K2.6Moonshot
868886888587
Nemotron 3 Ultra 550BNVIDIA
728582728878
MiniMax M3Minimax
508078509066
DeepSeek V4 FlashDeepSeek
456050407551
Step 3.7 FlashStepFun
528558508863
Qwen 3.6 27BAlibaba
557080508565
EXAONE 4.5 33BLG AI
557060507860
Solar Pro 3Upstage
587262528062
HyperCLOVAX SEED Think 32BNaver
406060408053
Qwen 3.5 9BAlibaba
386555357250
Kanana 2 30B-A3B ThinkingKakao
506855507257
Gemma 4 E2BGoogle
274226244030
Qwen 3.6 35B A3BAlibaba
305540255838
Mistral Small 4Mistral
255035205534
HyperCLOVAX SEED 1.5BNaver
233823193726
LFM2.5 8B-A1BLiquid AI
314529314134
GPT-5.5OpenAI
949494969495
Claude Sonnet 4.6Anthropic
929292959293
Gemini 3.5 FlashGoogle
909088928890
Gemini 3.1 ProGoogle
889088908588
Claude Opus 4.8Anthropic
929290939292
Qwen 3.7 MaxAlibaba
828882808583
DeepSeek V4 ProDeepSeek
909290928891
GPT-5.4 MiniOpenAI
858888858586
Gemma 4 31BGoogle
848684868485
Gemma 4 12BGoogle
828484848283
Mimo V2.5 ProXiaomi
687870657870
Gemma 4 26B A4BGoogle
828582858283
Gemini 3.1 Flash LiteGoogle
808382827881
Qwen 3.7 PlusAlibaba
768484748880
Kimi K2.6Moonshot
627568588067
Nemotron 3 Ultra 550BNVIDIA
608278588870
MiniMax M3Minimax
658888629276
DeepSeek V4 FlashDeepSeek
838585828584
Step 3.7 FlashStepFun
458552428858
Qwen 3.6 27BAlibaba
607580609071
EXAONE 4.5 33BLG AI
486848457554
Solar Pro 3Upstage
405545405045
HyperCLOVAX SEED Think 32BNaver
608040608062
Qwen 3.5 9BAlibaba
457260407555
Kanana 2 30B-A3B ThinkingKakao
406545387049
Gemma 4 E2BGoogle
394937354740
Qwen 3.6 35B A3BAlibaba
355840306242
Mistral Small 4Mistral
184025155027
HyperCLOVAX SEED 1.5BNaver
264025233829
LFM2.5 8B-A1BLiquid AI
213721163724