BuiltBench
Models match a building component description to the corresponding entry in a construction classification system.
The tasks use industry reference systems including IFC and Uniclass.
- Made by
- Mehrzad Shahinmoghadam and colleagues
- Released
- November 2024
- Kind
- CAD models
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Civil engineering
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- June 2025
- Scores refreshed
- November 20th, 2026
Alibaba-NLP/gte-Qwen2-7B-instruct tops the leaderboard with 68.6 Qwen3-Embedding-8B leads with 65.3
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Qwen3-Embedding-8B, at 65.3. This view shows only models we track, each at its best.
- 68.6 Alibaba-NLP/gte-Qwen2-7B-instruct
- 68.6 Linq-AI-Research/Linq-Embed-Mistral
- 67.6 codefuse-ai/F2LLM-v2-8B
- 67.4 codefuse-ai/F2LLM-v2-14B
- 67.3 Salesforce/SFR-Embedding-2_R
- 66.8 GritLM/GritLM-7B
- 66.8 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826
- 66.2 codefuse-ai/F2LLM-v2-4B
- 65.3 ai-sage/Giga-Embeddings-instruct-3B-0826
- 65.3
Qwen3-Embedding-8B
- 65.1 Alibaba-NLP/gte-Qwen2-1.5B-instruct
- 63.6 codefuse-ai/F2LLM-v2-1.7B
- 63.1 codefuse-ai/F2LLM-4B
- 62.5
Qwen3-Embedding-4B
- 60.6 NovaSearch/stella_en_1.5B_v5
- 60.0 infly/inf-retriever-v1-1.5b
- 59.8 thenlper/gte-large
- 59.0 mixedbread-ai/mxbai-embed-large-v1
- 58.9 codefuse-ai/F2LLM-v2-0.6B
- 58.8 VPLabs/SearchMap_Preview
- 58.5 codefuse-ai/F2LLM-1.7B
- 57.8 intfloat/multilingual-e5-large-instruct
- 57.7 avsolatorio/GIST-large-Embedding-v0
- 57.7 microsoft/harrier-oss-v1-270m
- 57.5 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
- 57.5 intfloat/e5-large
- 57.5 WhereIsAI/UAE-Large-V1
- 57.5 codefuse-ai/F2LLM-v2-330M
- 57.4 BAAI/bge-large-en-v1.5
- 57.4 google/embeddinggemma-300m
- 56.7 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
- 56.7 MongoDB/mdbr-leaf-mt
- 56.4 thenlper/gte-small
- 56.2 avsolatorio/GIST-Embedding-v0
- 56.1 prdev/mini-gte
- 56.1 avsolatorio/GIST-small-Embedding-v0
- 55.6 Lajavaness/bilingual-embedding-large
- 55.6 Alibaba-NLP/gte-multilingual-base
- 55.5 IEITYuan/Yuan-embedding-2.0-en
- 55.5 hotchpotch/bekko-embedding-v1-a25m
- 55.4 jinaai/jina-embeddings-v3
- 55.2 intfloat/e5-large-v2
- 55.1 Snowflake/snowflake-arctic-embed-l-v2.0
- 55.0 infgrad/Jasper-Token-Compression-600M
- 55.0 ibm-granite/granite-embedding-311m-multilingual-r2
- 55.0 BAAI/bge-base-en-v1.5
- 54.7 intfloat/e5-base-v2
- 54.6 Snowflake/snowflake-arctic-embed-m-v2.0
- 54.2 Mihaiii/gte-micro-v4
- 54.0 intfloat/e5-small
- 53.7 NovaSearch/stella_en_400M_v5
- 53.4 BAAI/bge-small-en-v1.5
- 53.3 intfloat/multilingual-e5-large
- 53.1 Mihaiii/Bulbasaur
- 52.8 sentence-transformers/all-MiniLM-L12-v2
- 52.7 hotchpotch/bekko-embedding-v1-a8m
- 52.5 jinaai/jina-embeddings-v2-small-en
- 52.1 intfloat/multilingual-e5-small
- 51.8 codefuse-ai/F2LLM-v2-160M
- 51.7 ibm-granite/granite-embedding-97m-multilingual-r2
- 51.6 minishlab/potion-base-32M
- 51.4 BAAI/bge-m3
- 50.5 codefuse-ai/F2LLM-v2-80M
- 49.2 manu/sentence_croissant_alpha_v0.3
- 48.1 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 45.4 sentence-transformers/static-similarity-mrl-multilingual-v1
- 43.5 minishlab/potion-multilingual-128M
- 1 Alibaba-NLP/gte-Qwen2-7B-instruct 68.6
- 2 Linq-AI-Research/Linq-Embed-Mistral 68.6
- 3 codefuse-ai/F2LLM-v2-8B 67.6
- 4 codefuse-ai/F2LLM-v2-14B 67.4
- 5 Salesforce/SFR-Embedding-2_R 67.3
- 6 GritLM/GritLM-7B 66.8
- 7 ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 66.8
- 8 codefuse-ai/F2LLM-v2-4B 66.2
- 9 ai-sage/Giga-Embeddings-instruct-3B-0826 65.3
- 10
Qwen3-Embedding-8B 65.3
- 11 Alibaba-NLP/gte-Qwen2-1.5B-instruct 65.1
- 12 codefuse-ai/F2LLM-v2-1.7B 63.6
- 13 codefuse-ai/F2LLM-4B 63.1
- 14
Qwen3-Embedding-4B 62.5
- 15 NovaSearch/stella_en_1.5B_v5 60.6
- 16 infly/inf-retriever-v1-1.5b 60.0
- 17 thenlper/gte-large 59.8
- 18 mixedbread-ai/mxbai-embed-large-v1 59.0
- 19 codefuse-ai/F2LLM-v2-0.6B 58.9
- 20 VPLabs/SearchMap_Preview 58.8
- 21 codefuse-ai/F2LLM-1.7B 58.5
- 22 intfloat/multilingual-e5-large-instruct 57.8
- 23 avsolatorio/GIST-large-Embedding-v0 57.7
- 24 microsoft/harrier-oss-v1-270m 57.7
- 25 KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 57.5
- 26 intfloat/e5-large 57.5
- 27 WhereIsAI/UAE-Large-V1 57.5
- 28 codefuse-ai/F2LLM-v2-330M 57.5
- 29 BAAI/bge-large-en-v1.5 57.4
- 30 google/embeddinggemma-300m 57.4
- 31 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 56.7
- 32 MongoDB/mdbr-leaf-mt 56.7
- 33 thenlper/gte-small 56.4
- 34 avsolatorio/GIST-Embedding-v0 56.2
- 35 prdev/mini-gte 56.1
- 36 avsolatorio/GIST-small-Embedding-v0 56.1
- 37 Lajavaness/bilingual-embedding-large 55.6
- 38 Alibaba-NLP/gte-multilingual-base 55.6
- 39 IEITYuan/Yuan-embedding-2.0-en 55.5
- 40 hotchpotch/bekko-embedding-v1-a25m 55.5
- 41 jinaai/jina-embeddings-v3 55.4
- 42 intfloat/e5-large-v2 55.2
- 43 Snowflake/snowflake-arctic-embed-l-v2.0 55.1
- 44 infgrad/Jasper-Token-Compression-600M 55.0
- 45 ibm-granite/granite-embedding-311m-multilingual-r2 55.0
- 46 BAAI/bge-base-en-v1.5 55.0
- 47 intfloat/e5-base-v2 54.7
- 48 Snowflake/snowflake-arctic-embed-m-v2.0 54.6
- 49 Mihaiii/gte-micro-v4 54.2
- 50 intfloat/e5-small 54.0
- 51 NovaSearch/stella_en_400M_v5 53.7
- 52 BAAI/bge-small-en-v1.5 53.4
- 53 intfloat/multilingual-e5-large 53.3
- 54 Mihaiii/Bulbasaur 53.1
- 55 sentence-transformers/all-MiniLM-L12-v2 52.8
- 56 hotchpotch/bekko-embedding-v1-a8m 52.7
- 57 jinaai/jina-embeddings-v2-small-en 52.5
- 58 intfloat/multilingual-e5-small 52.1
- 59 codefuse-ai/F2LLM-v2-160M 51.8
- 60 ibm-granite/granite-embedding-97m-multilingual-r2 51.7
- 61 minishlab/potion-base-32M 51.6
- 62 BAAI/bge-m3 51.4
- 63 codefuse-ai/F2LLM-v2-80M 50.5
- 64 manu/sentence_croissant_alpha_v0.3 49.2
- 65 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 48.1
- 66 sentence-transformers/static-similarity-mrl-multilingual-v1 45.4
- 67 minishlab/potion-multilingual-128M 43.5
Source: The BuiltBench paper
Source: The BuiltBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Alibaba-NLP/gte-Qwen2-7B-instruct open weights, 7.1B | 68.6 | Official leaderboard | ||
| 2 | Linq-AI-Research/Linq-Embed-Mistral open weights, 7.1B | 68.6 | Official leaderboard | ||
| 3 | codefuse-ai/F2LLM-v2-8B open weights, 7.6B | 67.6 | Official leaderboard | ||
| 4 | codefuse-ai/F2LLM-v2-14B open weights, 14B | 67.4 | Official leaderboard | ||
| 5 | Salesforce/SFR-Embedding-2_R open weights, 7.1B | 67.3 | Official leaderboard | ||
| 6 | GritLM/GritLM-7B open weights, 7.2B | 66.8 | Official leaderboard | ||
| 7 | ai-sage/Giga-Embeddings-instruct-10B-A1.8B-0826 open weights, 10.5B | 66.8 | Official leaderboard | ||
| 8 | codefuse-ai/F2LLM-v2-4B open weights, 4B | 66.2 | Official leaderboard | ||
| 9 | ai-sage/Giga-Embeddings-instruct-3B-0826 open weights, 3.2B | 65.3 | Official leaderboard | ||
| 10 | | 65.3 | Jun 2025 | Official leaderboard | |
| 11 | Alibaba-NLP/gte-Qwen2-1.5B-instruct open weights, 1.5B | 65.1 | Official leaderboard | ||
| 12 | codefuse-ai/F2LLM-v2-1.7B open weights, 1.7B | 63.6 | Official leaderboard | ||
| 13 | codefuse-ai/F2LLM-4B open weights, 4B | 63.1 | Official leaderboard | ||
| 14 | | 62.5 | Jun 2025 | Official leaderboard | |
| 15 | NovaSearch/stella_en_1.5B_v5 open weights, 1.5B | 60.6 | Official leaderboard | ||
| 16 | infly/inf-retriever-v1-1.5b open weights, 1.5B | 60.0 | Official leaderboard | ||
| 17 | thenlper/gte-large open weights, 0.3B | 59.8 | Official leaderboard | ||
| 18 | mixedbread-ai/mxbai-embed-large-v1 open weights, 0.3B | 59.0 | Official leaderboard | ||
| 19 | codefuse-ai/F2LLM-v2-0.6B open weights, 0.6B | 58.9 | Official leaderboard | ||
| 20 | VPLabs/SearchMap_Preview open weights, 0.4B | 58.8 | Official leaderboard | ||
| 21 | codefuse-ai/F2LLM-1.7B open weights, 1.7B | 58.5 | Official leaderboard | ||
| 22 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 57.8 | Official leaderboard | ||
| 23 | avsolatorio/GIST-large-Embedding-v0 open weights, 0.3B | 57.7 | Official leaderboard | ||
| 24 | microsoft/harrier-oss-v1-270m open weights, 0.3B | 57.7 | Official leaderboard | ||
| 25 | KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 open weights, 0.5B | 57.5 | Official leaderboard | ||
| 26 | intfloat/e5-large open weights, 0.3B | 57.5 | Official leaderboard | ||
| 27 | WhereIsAI/UAE-Large-V1 open weights, 0.3B | 57.5 | Official leaderboard | ||
| 28 | codefuse-ai/F2LLM-v2-330M open weights, 0.3B | 57.5 | Official leaderboard | ||
| 29 | BAAI/bge-large-en-v1.5 open weights, 0.3B | 57.4 | Official leaderboard | ||
| 30 | google/embeddinggemma-300m open weights, 0.3B | 57.4 | Official leaderboard | ||
| 31 | HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1 open weights, 0.5B | 56.7 | Official leaderboard | ||
| 32 | MongoDB/mdbr-leaf-mt open weights, 0B | 56.7 | Official leaderboard | ||
| 33 | thenlper/gte-small open weights, 0B | 56.4 | Official leaderboard | ||
| 34 | avsolatorio/GIST-Embedding-v0 open weights, 0.1B | 56.2 | Official leaderboard | ||
| 35 | prdev/mini-gte open weights, 0.1B | 56.1 | Official leaderboard | ||
| 36 | avsolatorio/GIST-small-Embedding-v0 open weights, 0B | 56.1 | Official leaderboard | ||
| 37 | Lajavaness/bilingual-embedding-large open weights, 0.6B | 55.6 | Official leaderboard | ||
| 38 | Alibaba-NLP/gte-multilingual-base open weights, 0.3B | 55.6 | Official leaderboard | ||
| 39 | IEITYuan/Yuan-embedding-2.0-en open weights, 0.6B | 55.5 | Official leaderboard | ||
| 40 | hotchpotch/bekko-embedding-v1-a25m open weights, 0.1B | 55.5 | Official leaderboard | ||
| 41 | jinaai/jina-embeddings-v3 open weights, 0.6B | 55.4 | Official leaderboard | ||
| 42 | intfloat/e5-large-v2 open weights, 0.3B | 55.2 | Official leaderboard | ||
| 43 | Snowflake/snowflake-arctic-embed-l-v2.0 open weights, 0.6B | 55.1 | Official leaderboard | ||
| 44 | infgrad/Jasper-Token-Compression-600M open weights, 0.6B | 55.0 | Official leaderboard | ||
| 45 | ibm-granite/granite-embedding-311m-multilingual-r2 open weights, 0.3B | 55.0 | Official leaderboard | ||
| 46 | BAAI/bge-base-en-v1.5 open weights, 0.1B | 55.0 | Official leaderboard | ||
| 47 | intfloat/e5-base-v2 open weights, 0.1B | 54.7 | Official leaderboard | ||
| 48 | Snowflake/snowflake-arctic-embed-m-v2.0 open weights, 0.3B | 54.6 | Official leaderboard | ||
| 49 | Mihaiii/gte-micro-v4 open weights, 0B | 54.2 | Official leaderboard | ||
| 50 | intfloat/e5-small open weights, 0B | 54.0 | Official leaderboard | ||
| 51 | NovaSearch/stella_en_400M_v5 open weights, 0.4B | 53.7 | Official leaderboard | ||
| 52 | BAAI/bge-small-en-v1.5 open weights, 0B | 53.4 | Official leaderboard | ||
| 53 | intfloat/multilingual-e5-large open weights, 0.6B | 53.3 | Official leaderboard | ||
| 54 | Mihaiii/Bulbasaur open weights, 0B | 53.1 | Official leaderboard | ||
| 55 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | 52.8 | Official leaderboard | ||
| 56 | hotchpotch/bekko-embedding-v1-a8m open weights, 0.1B | 52.7 | Official leaderboard | ||
| 57 | jinaai/jina-embeddings-v2-small-en open weights, 0B | 52.5 | Official leaderboard | ||
| 58 | intfloat/multilingual-e5-small open weights, 0.1B | 52.1 | Official leaderboard | ||
| 59 | codefuse-ai/F2LLM-v2-160M open weights, 0.2B | 51.8 | Official leaderboard | ||
| 60 | ibm-granite/granite-embedding-97m-multilingual-r2 open weights, 0.1B | 51.7 | Official leaderboard | ||
| 61 | minishlab/potion-base-32M open weights, 0B | 51.6 | Official leaderboard | ||
| 62 | BAAI/bge-m3 open weights, 0.6B | 51.4 | Official leaderboard | ||
| 63 | codefuse-ai/F2LLM-v2-80M open weights, 0.1B | 50.5 | Official leaderboard | ||
| 64 | manu/sentence_croissant_alpha_v0.3 open weights, 1.3B | 49.2 | Official leaderboard | ||
| 65 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 48.1 | Official leaderboard | ||
| 66 | sentence-transformers/static-similarity-mrl-multilingual-v1 open weights, 0.1B | 45.4 | Official leaderboard | ||
| 67 | minishlab/potion-multilingual-128M open weights, 0.1B | 43.5 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 65.3 | Jun 2025 | Official leaderboard | |
| 2 | | 62.5 | Jun 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official BuiltBench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Engineering and CAD
- EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge.
Gemini 4 Carbon 83.9%
- 3DCodeBench In use Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity.
LongCat-2.5 55.4%
- CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
- PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%
- Razavi-Bench Not in model cards Models explain what happens in analog circuits and why. A language model awards up to four points per answer against a reference and a rubric.
Gemini 4 Carbon 98.3%
- CircuitRubric Not in model cards Models write analog circuit netlists from design requests. A program compares transistor connections and relative device sizes with accepted reference circuits. Claude Opus 4.8 96%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 17 months ago, in June 2025, for Qwen3-Embedding-4B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (67 entries).
- Pass Models scored 2 models we track, plus 65 other entries on its leaderboard.
- Warning Newest score The newest came 17 months ago, in June 2025, for Qwen3-Embedding-4B.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 2 rows for models we track and 65 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.