diff --git a/docs/benchmarks.md b/docs/benchmarks.md
index f2fbd191..4f686a10 100644
--- a/docs/benchmarks.md
+++ b/docs/benchmarks.md
@@ -179,11 +179,14 @@ Two approaches are benchmarked separately:
 
 ##### Skill QA + citation retrieval
 
-| Embedding Model        | VLM                  | Skill model      | QA accuracy | Mean `cited_map` |
-|------------------------|----------------------|------------------|-------------|------------------|
-| `qwen3-embedding:4b`   | Ollama / ministral-3 | `ollama:gpt-oss` | 0.94        | 0.86             |
+| Embedding Model        | VLM                  | Skill model                  | QA accuracy | Mean `cited_map` |
+|------------------------|----------------------|------------------------------|-------------|------------------|
+| `qwen3-embedding:4b`   | Ollama / ministral-3 | `ollama:gpt-oss`             | 0.94        | 0.86             |
+| `qwen3-embedding:4b`   | Ollama / ministral-3 | `vllm:Gemma-4-26B-A4B-NVFP4` | 0.90        | 0.89             |
 
-*Measured on haiku.rag v0.44.0, judged by `ollama:qwen3.6` (current default), on 2992 of 3044 completed cases.*
+*`ollama:gpt-oss` row measured on haiku.rag v0.44.0, on 2992 of 3044 completed cases.*
+*`vllm:Gemma-4-26B-A4B-NVFP4` row measured on haiku.rag v0.47.0, with `mxbai-rerank-base-v2`, stopped at 674 of 3045 cases (cumulative means stable from case ~200).*
+*Both judged by `ollama:qwen3.6` (current default).*
 
 ## Past results