benchmark figure

content/20.results.md

@@ -83,8 +83,12 @@ Consequently, the models without prompt engine show a lower performance in creat
 ![
 **Benchmark results.**
 A) Performance of different LLMs on the BioChatter benchmark datasets.
-B) Performance of different LLMs with and without the use of BioChatter's prompt engine for KG querying.
-](images/benchmark_results.png "Benchmark results"){#fig:benchmark}
+While the closed-source models from OpenAI show consistently highest performance, some open-source models are comparable.
+However, the measured performance does not correlate intuitively with the size and quantisation (bit-precision) of the models.
+Some smaller models perform better than larger ones, even within the same model family; while very low bit-precision (2-bit) expectedly yields worse performance, the same is true for the high end (8-bit).
+*: Of note, many characteristics of OpenAI models are not public, and thus their bit-precision (as well as the exact size of GPT4) is subject to speculation.
+B) Comparison of the two benchmark tasks for KG querying show the superior performance of BioChatter's prompt engine. The BioChatter variant involves a multi-step procedure of constructing the query, while the "naive" version only receives the complete schema definition of the BioCypher KG (which BioChatter also uses as a basis for the prompt engine). The general instructions for both variants are the same, otherwise.
+](images/biochatter-benchmark.png "Benchmark results"){#fig:benchmark}
 
 ### Knowledge Graphs