A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline

A developer built a Code-RAG benchmark on Apache Kafka 4.0.0 to study how retrieval pipeline choices affect model rankings. Comparing 16 embedding models, 5 chunking strategies, and 3 retrieval modes across 30 questions, the results show that model rankings are not absolute but depend on specific configurations like chunking, retrieval mode, and query phrasing.

When developers enter an unfamiliar project, they rarely search for a specific file by name. They usually ask about system behavior: where incoming connections are accepted, which component cleans logs, or how a request travels between architectural layers. Code-RAG tries to answer such questions through semantic search. It splits and indexes the source code, then retrieves the context most closely related to a developer's query. The quality of this search is often reduced to the choice of embedding model: compare several candidates and select the one with the highest metric. In practice, the result also depends on how the code was split and which retrieval mode was used. To study these dependencies, I built a Code-RAG benchmark on the Apache Kafka 4.0.0 broker core, a real polyglot project written in Java and Scala. For thirty questions about system behavior, I identified the correct files in advance, allowing me to measure how accurately the retrieval pipeline finds the relevant code. The results show that a model ranking exists only within a specific configuration. Changing the chunking strategy, retrieval mode, or query phrasing can change both the metric value and the order of models in the ranking. In this part of the study, I compare sixteen embedding models, five chunking configurations, and three retrieval modes: BM25, vector search, and hybrid search. Each of the thirty questions was expressed in five forms, ranging from a natural developer question to a query with inaccurate terminology or a reference to a neighboring module. The structure of these variants and the evaluation methodology are described in Part 1 of the study https://dev.to/miftakhov/a-cognitive-benchmark-for-code-rag-retrieval-part-1-methodology-3m7l . I compared four groups of variables: | Variable | What changed | What it tested | |---|---|---| | Embedding model | 7 local models through Ollama and 9 commercial APIs | How strongly quality depends on the vector representation of the query and code | | Chunking | Whole-file indexing and four fixed-size chunks with overlap | How the indexed fragment size affects a particular model | | Retrieval mode | BM25 ONLY , VECTOR ONLY , HYBRID RRF | Whether lexical search, vector search, or their combination works best | | Query phrasing | Natural question, technical query, keywords, inaccurate terminology, and selected cross-module queries | How strongly the result depends on the language of the query | The three retrieval modes work as follows: | Mode | How the ranking is produced | |---|---| BM25 ONLY | Lucene lexical search. Files rank highly when query terms match terms in the code. No embedding model is used. | VECTOR ONLY | The query and code fragments are converted into embeddings. Ranking is based on vector similarity, so exact word overlap is unnecessary. | HYBRID RRF | BM25 and vector search run independently, then their positions are combined using Reciprocal Rank Fusion. RRF uses rank positions rather than directly adding incomparable scores. | The primary metric in this article is recall@10 . For a single question, it equals 1 when the primary correct file appears in the first ten results and 0 otherwise. The final value is the average across thirty questions. For example, recall@10 = 0.900 means that the correct file appeared in the top ten for 27 of 30 questions. The model ranking also reports a 95% CI , a 95% bootstrap confidence interval. To calculate it, I repeatedly resampled the set of questions with replacement and recalculated recall for each sample. A wide interval means that thirty questions are insufficient for precisely estimating small differences. Overlapping intervals are not themselves a formal pairwise test, but they warn against treating the order of neighboring rows as stable. The chunking label c500-o100 means fragments of 500 characters with a 100-character overlap. whole-file means that an entire file is indexed as one fragment. I did not test the complete Cartesian product of all parameters. Models were compared under a fixed baseline configuration; local and commercial models were tested across five chunking configurations; and VECTOR ONLY was compared with HYBRID RRF at the fixed c1500-o200 chunking. The full interaction between retrieval mode and chunking remained outside the study. BM25 was run as a single baseline because it does not depend on an embedding model. To compare embedding models, the remaining retrieval-pipeline parameters must be fixed. Otherwise, it is impossible to tell whether a difference was caused by the model, fragment size, or retrieval method. The baseline comparison used natural human questions, HYBRID RRF , and c1500-o200 chunking. For each model, I measured the share of thirty questions for which the correct file appeared in the first ten results. This ranking compares models under identical conditions, but it does not describe their quality outside the selected configuration. For example, OpenAI text-embedding-3-large achieved recall@10 = 0.833 with c1500-o200 , 0.900 with the smaller c500-o100 fragments, and 0.433 when files were indexed whole. The value 0.833 therefore cannot be treated as an independent property of the model. It describes one combination of model, chunking, retrieval mode, corpus, and question set. The baseline ranking is a useful starting point, but it cannot identify the best configuration without testing the other parameters. Ideally, code should be split along logical boundaries such as methods, classes, or other structural units. Structural chunking, however, requires a dedicated parser for every language. This study deliberately uses a polyglot Java and Scala project. I therefore split the code into fixed-size fragments. This is not presented as the optimal way to index code; it provides a common denominator across languages and makes it possible to isolate the effect of fragment size. Every value in the table is recall@10 for natural human questions using hybrid retrieval. The best observed result for each model is shown in bold. | Model | c500-o100 | c1500-o200 | c3000-o300 | c5000-o500 | whole-file | Type | |---|---|---|---|---|---|---| | all-minilm | 0.733 | 0.700 | 0.667 | 0.700 | 0.567 | local | | bge-m3 | 0.833 | 0.767 | 0.767 | 0.633 | 0.733 | local | | granite-embedding | 0.800 | 0.767 | 0.767 | 0.633 | 0.433 | local | | mxbai-embed-large | 0.900 | 0.833 | 0.733 | 0.633 | 0.433 | local | | nomic-embed-text | 0.733 | 0.667 | 0.700 | 0.633 | 0.133 | local | | qwen3-embedding:0.6b | 0.800 | 0.800 | 0.933 | 0.833 | 0.900 | local | | snowflake-arctic-embed2 | 0.800 | 0.800 | 0.800 | 0.733 | 0.733 | local | | EmbeddingsGigaR | 0.767 | 0.767 | 0.800 | 0.789 | 0.167 | commercial | | GigaEmbeddings-3B | 0.767 | 0.867 | 0.833 | 0.767 | 0.300 | commercial | | codestral-embed | 0.800 | 0.900 | 0.867 | 0.800 | 0.467 | commercial | | mistral-embed-2312 | 0.800 | 0.800 | 0.900 | 0.800 | 0.400 | commercial | | text-embedding-3-large | 0.900 | 0.833 | 0.867 | 0.800 | 0.433 | commercial | | text-embedding-3-small | 0.867 | 0.867 | 0.867 | 0.867 | 0.433 | commercial | | voyage-4-large | 0.900 | 0.833 | 0.867 | 0.833 | 0.867 | commercial | | voyage-code-2 | 0.933 | 0.867 | 0.800 | 0.800 | 0.533 | commercial | | voyage-code-3 | 0.900 | 0.867 | 0.900 | 0.833 | 0.833 | commercial | For five of the seven local models, c500-o100 produced the highest observed result. One possible explanation is that a small fragment contains less unrelated code. Its embedding can describe a local implementation more precisely, while BM25 benefits from matching specific terms. The experiment does not establish this mechanism directly. Doing so would require inspecting retrieved fragments and comparing hybrid and vector-only search at every chunk size. qwen3-embedding:0.6b achieved its highest result with c3000-o300 and still reached 0.900 when indexing whole files. Unlike most local models, it retained quality on larger fragments. A possible explanation is the model's ability to process longer context. A larger fragment preserves relationships between methods and their surrounding class that smaller fragments may lose. A similar pattern appeared for mistral-embed-2312 , EmbeddingsGigaR , and partly for voyage-code-3 . This remains a hypothesis: the experiment measured retrieval outcomes, not the internal cause of each model's behavior. With whole-file , results ranged from 0.133 to 0.900 . The approach remained viable for qwen3-embedding , voyage-4-large , and voyage-code-3 , but quality dropped sharply for nomic-embed-text and EmbeddingsGigaR . The likely explanation is context-window limits and truncation of long files. Because I did not directly measure truncation by provider tokenizers, this must also remain a hypothesis. The matrix does not reveal a universally best fragment size. Instead, it shows three kinds of behavior: Chunking should therefore be selected together with the embedding model. When tuning time is limited, c500-o100 is a reasonable starting point, but at least one larger alternative should also be tested, and whole-file should not be used without separate validation. After choosing how to split the code, the next question is how to retrieve the relevant fragments. The experiment compared three modes: BM25 ONLY matches words in the query against words in the code; VECTOR ONLY compares semantic similarity between embeddings; HYBRID RRF combines the rank positions from BM25 and vector search.The retrieval-mode comparison used c1500-o200 . In an earlier experiment, the combination c1500-o200 + HYBRID RRF produced the strongest result available at the time and became the control configuration for later runs. The subsequent chunking matrix showed that there is no universally optimal fragment size. Keeping c1500-o200 , however, allowed retrieval modes to be compared under identical conditions without mixing their effect with a chunking change. The full matrix of retrieval modes and chunking configurations was not tested. The results below therefore describe retrieval-mode behavior only at c1500-o200 . Every value is recall@10 for natural human questions. The best mode for each model is shown in bold. | Model | BM25 ONLY | VECTOR ONLY | HYBRID RRF | Type | |---|---|---|---|---| | No embedding model | 0.600 | — | — | lexical baseline | | all-minilm | — | 0.667 | 0.700 | local | | bge-m3 | — | 0.867 | 0.767 | local | | granite-embedding | — | 0.733 | 0.767 | local | | mxbai-embed-large | — | 0.833 | 0.833 | local | | nomic-embed-text | — | 0.667 | 0.667 | local | | qwen3-embedding:0.6b | — | 0.800 | 0.800 | local | | snowflake-arctic-embed2 | — | 0.900 | 0.800 | local | | EmbeddingsGigaR | — | 0.711 | 0.767 | commercial | | GigaEmbeddings-3B | — | 0.833 | 0.867 | commercial | | codestral-embed | — | 0.967 | 0.900 | commercial | | mistral-embed-2312 | — | 0.900 | 0.800 | commercial | | text-embedding-3-large | — | 0.867 | 0.833 | commercial | | text-embedding-3-small | — | 0.833 | 0.867 | commercial | | voyage-4-large | — | 0.878 | 0.833 | commercial | | voyage-code-2 | — | 0.933 | 0.867 | commercial | | voyage-code-3 | — | 0.933 | 0.867 | commercial | Commercial-model values are averaged across three repeated runs, so some values are not multiples of one question out of thirty. Adding BM25 to vector search helped two local and three commercial models. It made no difference for three local models. In the remaining cases, hybrid retrieval reduced recall@10 . Among local models, the clearest differences appeared for bge-m3 and snowflake-arctic-embed2 : vector-only search improved their results by 0.100 . Among commercial models, mistral-embed-2312 showed the same improvement. One possible explanation is that BM25 helps when the correct file contains query terms missed by vector search. It can also promote lexically similar but semantically incorrect files and weaken an already strong vector ranking. The experiment did not test this mechanism directly. For natural questions, BM25 achieved recall@10 = 0.600 , below every tested embedding-based combination. Its result, however, depended strongly on query language. For queries composed of technical terms and keywords, BM25 reached 0.833–0.867 . With inaccurate terminology, it fell to 0.400 . Lexical search works well when the developer already knows the names of relevant entities, but it is less effective when system behavior is described in the developer's own words. The choice of retrieval mode, like the choice of chunking, depends on the embedding model. Hybrid retrieval cannot be assumed to improve vector search: it helped some models, left some unchanged, and reduced the results of others. A practical evaluation should compare at least VECTOR ONLY and HYBRID RRF on the selected model and representative queries. BM25 remains both a useful control point and a standalone option for precise technical searches. The same question about code can be expressed in different ways. A developer may describe system behavior in natural language, list known technical terms, or use a plausible but incorrect name for a component. To test retrieval robustness under these changes, each question was represented in several forms: human — a natural developer question; ai optimized — a detailed query using precise technical terminology; keyword — a short list of keywords; wrong terminology — the original intent with one controlled terminology error; cross module — a question connecting multiple system components.The construction rules for these variants are described in Part 1 of the study https://dev.to/miftakhov/a-cognitive-benchmark-for-code-rag-retrieval-part-1-methodology-3m7l . This comparison fixed chunking at c1500-o200 and used HYBRID RRF . Every value is recall@10 . The cross module variant existed for only ten applicable questions, while the other results were calculated across all thirty. | Model | human | ai optimized | keyword | wrong terminology | cross module | Type | |---|---|---|---|---|---|---| | BM25 without an embedding model | 0.600 | 0.833 | 0.867 | 0.400 | 0.600 | baseline | | all-minilm | 0.700 | 0.933 | 0.933 | 0.433 | 0.600 | local | | bge-m3 | 0.767 | 1.000 | 0.833 | 0.633 | 0.700 | local | | granite-embedding | 0.767 | 1.000 | 0.967 | 0.567 | 0.700 | local | | mxbai-embed-large | 0.833 | 0.967 | 0.867 | 0.633 | 0.700 | local | | nomic-embed-text | 0.667 | 0.700 | 0.733 | 0.467 | 0.700 | local | | qwen3-embedding:0.6b | 0.800 | 1.000 | 0.900 | 0.600 | 0.700 | local | | snowflake-arctic-embed2 | 0.800 | 1.000 | 1.000 | 0.633 | 0.700 | local | | EmbeddingsGigaR | 0.767 | 1.000 | 0.900 | 0.600 | 0.700 | commercial | | GigaEmbeddings-3B | 0.867 | 1.000 | 0.800 | 0.633 | 0.700 | commercial | | codestral-embed | 0.900 | 1.000 | 1.000 | 0.667 | 0.700 | commercial | | mistral-embed-2312 | 0.800 | 1.000 | 1.000 | 0.633 | 0.700 | commercial | | text-embedding-3-large | 0.833 | 1.000 | 0.933 | 0.600 | 0.700 | commercial | | text-embedding-3-small | 0.867 | 1.000 | 0.967 | 0.567 | 0.700 | commercial | | voyage-4-large | 0.833 | 1.000 | 1.000 | 0.733 | 0.700 | commercial | | voyage-code-2 | 0.867 | 1.000 | 1.000 | 0.700 | 0.700 | commercial | | voyage-code-3 | 0.867 | 1.000 | 1.000 | 0.700 | 0.700 | commercial | The ai optimized variant contains class names, component names, and operations already present in the code. On these queries, all nine commercial and four of the seven local models reached recall@10 = 1.000 . This does not mean that code retrieval is solved. It shows that Code-RAG works far better when the user already knows the terminology and approximate location of the answer. In practice, retrieval is often needed precisely because that knowledge is missing. Short keyword queries also performed well. Even BM25 reached 0.867 , because the keywords often matched names and terms in the source code directly. Replacing one term with a plausible but incorrect alternative reduced the result of every tested model. Among commercial models, the drop relative to human ranged from 0.100 for voyage-4-large to 0.300 for text-embedding-3-small . The model ranked first on natural questions was not the most robust to terminology distortion. codestral-embed fell from 0.900 to 0.667 , while voyage-4-large fell from 0.833 to 0.733 . Code specialization also failed to predict robustness. The smallest and largest observed drops among commercial models both belonged to general-purpose models. The cross module values barely distinguish the embedding models: every model except all-minilm received 0.700 , while all-minilm received 0.600 . This variant existed for only ten questions, so the result cannot be interpreted as evidence of equal robustness. A meaningful comparison would require a separate question set focused on relationships between modules and containing more examples of this type. Query phrasing is another parameter of the retrieval pipeline. Precise terminology can bring almost every model close to the maximum result, while a small terminology error can reduce quality substantially. Model selection should therefore account for where queries come from. A system for developers familiar with the codebase and a system for new team members or non-technical users may require different configurations. For the baseline comparison, every model ran under the same conditions: natural human questions, HYBRID RRF , and c1500-o200 chunking. | Rank | Model | Model types in row | Recall@10 | 95% CI | |---|---|---|---|---| | 1 | mistral/codestral-embed | commercial | 0.900 | 0.800–1.000 | | 2–5 | GigaEmbeddings-3B, text-embedding-3-small, voyage-code-2, voyage-code-3 | commercial | 0.867 | 0.733–0.967 | | 6–8 | mxbai-embed-large, text-embedding-3-large, voyage-4-large | local and commercial | 0.833 | 0.700–0.967 | | 9–11 | qwen3-embedding:0.6b, snowflake-arctic-embed2 | local | 0.800 | 0.633–0.933 | | 9–11 | mistral-embed-2312 | commercial | 0.800 | 0.666–0.933 | | 12–14 | bge-m3, granite-embedding, EmbeddingsGigaR | local and commercial | 0.767 | 0.600–0.900 | | 15 | all-minilm | local | 0.700 | 0.533–0.867 | | 16 | nomic-embed-text | local | 0.667 | 0.500–0.833 | At first glance, this looks like a conventional ranking: a specialized commercial model takes first place, and the remaining results gradually fall from 0.867 to 0.667 . With thirty questions, however, a difference of 0.033 represents only one retrieved file. One question separates codestral-embed from the next four models. Those four retrieved the correct files for the same 26 questions out of 30, while the leader retrieved one additional file. A paired bootstrap analysis showed that the confidence interval for every pairwise difference among the top five models included zero. The available data is therefore insufficient to treat their order as stable. The separation between local and commercial models was also less pronounced than expected. Local mxbai-embed-large achieved 0.833 , two correct answers behind the leader out of thirty, and its confidence interval overlaps those of commercial models. Larger and more expensive models did not always produce better results. text-embedding-3-large achieved 0.833 , while the cheaper text-embedding-3-small reached 0.867 . The compact 62 MB granite-embedding tied the 1.2 GB bge-m3 at 0.767 . Two generations of specialized Voyage models, voyage-code-2 and voyage-code-3 , also completed the baseline comparison with the same result of 0.867 . These observations do not prove that the models are equal: thirty questions are insufficient for confidently comparing small differences. They do show why an embedding-model ranking is meaningful only together with its measurement conditions. Changing chunking, retrieval mode, or query phrasing can alter both the metric and the order of models in the table. The experiment does not identify one configuration suitable for every Code-RAG project. The decision depends on the queries the system will receive, where it will run, and how much time is available for tuning. | Requirement | Candidate | Evidence from this study | |---|---|---| Highest observed recall@10 | codestral-embed + c1500-o200 + VECTOR ONLY | Highest point estimate among completed runs: 0.967 | | No commercial APIs | qwen3-embedding:0.6b + c3000-o300 | Highest tuned local-model result: 0.933 | | Minimal initial tuning | voyage-4-large or voyage-code-3 | Smallest observed range across chunking configurations: 0.067 | | Restricted memory | granite-embedding | A 62 MB model with the same baseline point estimate, 0.767 , as the 1.2 GB bge-m3 | | Precise technical queries | BM25 as standalone search or a baseline | BM25 reached recall@10 = 0.867 on keyword queries without embedding infrastructure | | Inaccurate user queries | Vector or hybrid retrieval after testing the chosen model | The advantage of semantic retrieval over BM25 was most visible with inaccurate terminology | These candidates reflect the best observed results inside the experiment, not universal production configurations. For example, codestral-embed produced the highest recall@10 , but its advantage was measured at one chunking configuration, and statistical superiority over nearby models was not established. Local models avoid API charges but move cost into hardware and operations. Practical Code-RAG tuning should begin with a description of future queries, not a large model leaderboard. If the system is used by developers familiar with project terminology, BM25 may be a strong starting point. If questions come from new team members or users describing behavior in their own words, semantic retrieval becomes more important. The next step is to choose a short list of models that meet cost, memory, and deployment constraints. For each candidate, test several fragment sizes, then compare VECTOR ONLY and HYBRID RRF . A chunking or retrieval-mode choice should not be transferred from one model to another without retesting. The final comparison should include not only convenient technical queries, but also natural phrasing, inaccurate terminology, and plausible but incorrect files. Results should be retained per question so that an apparent advantage can be traced to a stable pattern rather than a few favorable examples. In practice, selecting a Code-RAG configuration becomes a process of narrowing the search space: The central result of this study is that an embedding model cannot be evaluated independently from the retrieval pipeline around it. Each model has its own effective combination of chunking, retrieval mode, and query phrasing. These parameters are connected. Fragment size determines how much code enters an embedding. Retrieval mode sets the balance between semantic similarity and exact terminology. Query phrasing determines how easily the system can connect a developer's intent to the vocabulary of the source code. There is therefore no universal ranking of Code-RAG models. Models can only be compared under explicit conditions: on a particular codebase, with a selected chunking strategy and retrieval mode, and for a known distribution of user queries. The practical question is not "Which model is best?" but "Which configuration best solves the tasks of this project's users?" Answering it requires joint tuning of the pipeline and evaluation on a project-specific question set. This study used one polyglot project and a small gold set, so its selected configurations should not be transferred to other codebases without retesting. Part 3 will describe the reproducible benchmark harness used to run these comparisons. The raw results are published with the project. The main tables in this article can be verified using these artifacts: results/E003-full/all.parquet results/E007-commercial-chunking-merged/all.parquet results/E004-vector/all.parquet results/E005-production/all.parquet results/E006-production-merged/all.parquet results/E007-commercial-vector-merged/all.parquet results/E004-bm25/all.parquet results/forest plot data.csv The confidence intervals for the baseline ranking can be recalculated from the source CSV files: git clone https://github.com/Daeryss/karta-rag-map cd karta-rag-map python3 -m venv .venv .venv/bin/pip install -r scripts/requirements.txt .venv/bin/python scripts/bootstrap cis.py \ results/E005-production/all.csv \ results/E006-production-merged/all.csv The script fixes the baseline conditions at k=10 , the human query variant, 2,000 bootstrap samples, and seed 42 . A Cognitive Benchmark for Code-RAG Retrieval · Part 2 of 3 · Previous: Part 1 — Methodology · Next: Part 3 — Engineering a Reproducible Benchmark