diff --git a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/information.txt b/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/information.txt
deleted file mode 100644
index 1fa6eafc..00000000
--- a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/information.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-CyberMetric Evaluation
-=====================
-
-Model: ollama/qwen2.5:14b
-Dataset: CyberMetric-2-v1.json
-Start Time: 2025-05-08 12:31:39
-Status: Completed
-Questions Processed: 2
-Correct Answers: 1
-Accuracy: 50.00%
-End Time: 2025-05-08 12:31:42
-Duration: 0:00:02.434703
diff --git a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/report_failed_questions.json b/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/report_failed_questions.json
deleted file mode 100644
index 04c365cb..00000000
--- a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-5zd6a/report_failed_questions.json
+++ /dev/null
@@ -1,15 +0,0 @@
-{
-    "questions": [
-        {
-            "question": "Which of the following is a desirable property of a biometric system?",
-            "answers": {
-                "A": "Permanent",
-                "B": "Transferability",
-                "C": "Uniformity",
-                "D": "Forgiveness"
-            },
-            "solution": "A",
-            "llm_answer": "C"
-        }
-    ]
-}
\ No newline at end of file
diff --git a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/information.txt b/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/information.txt
deleted file mode 100644
index 4fb1aa66..00000000
--- a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/information.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-CyberMetric Evaluation
-=====================
-
-Model: ollama/qwen2.5:14b
-Dataset: CyberMetric-2-v1.json
-Start Time: 2025-05-08 12:23:35
-Status: Completed
-Questions Processed: 2
-Correct Answers: 1
-Accuracy: 50.00%
-End Time: 2025-05-08 12:23:38
-Duration: 0:00:02.306513
diff --git a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/report_failed_questions.json b/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/report_failed_questions.json
deleted file mode 100644
index 04c365cb..00000000
--- a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08-sebps/report_failed_questions.json
+++ /dev/null
@@ -1,15 +0,0 @@
-{
-    "questions": [
-        {
-            "question": "Which of the following is a desirable property of a biometric system?",
-            "answers": {
-                "A": "Permanent",
-                "B": "Transferability",
-                "C": "Uniformity",
-                "D": "Forgiveness"
-            },
-            "solution": "A",
-            "llm_answer": "C"
-        }
-    ]
-}
\ No newline at end of file
diff --git a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08/information.txt b/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08/information.txt
deleted file mode 100644
index d32aedc2..00000000
--- a/benchmarks/cybermetric/output_cybermetric/ollama-qwen2.5:14b-2025-05-08/information.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-CyberMetric Evaluation
-=====================
-
-Model: ollama/qwen2.5:14b
-Dataset: CyberMetric-2-v1.json
-Start Time: 2025-05-08 12:22:51
-Status: Running
-Questions Processed: 0
-Correct Answers: 0
-Accuracy: 0.00%
diff --git a/benchmarks/cybermetric/output_cybermetric/openrouter-qwen-qwen3-32b:free-2025-05-08/information.txt b/benchmarks/cybermetric/output_cybermetric/openrouter-qwen-qwen3-32b:free-2025-05-08/information.txt
deleted file mode 100644
index 83b9626f..00000000
--- a/benchmarks/cybermetric/output_cybermetric/openrouter-qwen-qwen3-32b:free-2025-05-08/information.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-CyberMetric Evaluation
-=====================
-
-Model: openrouter/qwen/qwen3-32b:free
-Dataset: CyberMetric-2-v1.json
-Start Time: 2025-05-08 12:23:53
-Status: Running
-Questions Processed: 0
-Correct Answers: 0
-Accuracy: 0.00%
diff --git a/benchmarks/otros/cybermetric b/benchmarks/otros/cybermetric
new file mode 160000
index 00000000..2d82e92d
--- /dev/null
+++ b/benchmarks/otros/cybermetric
@@ -0,0 +1 @@
+Subproject commit 2d82e92dd6171a3fd5b40f8306af3b8c366179e6
diff --git a/ci/benchmark/.benchmark.yml b/ci/benchmark/.benchmark.yml
index 65ae2260..e230df4d 100644
--- a/ci/benchmark/.benchmark.yml
+++ b/ci/benchmark/.benchmark.yml
@@ -1,11 +1,11 @@
 use_base_container: &use_base_container
-  stage: test
+  stage: benchmark
   image: "${CI_REGISTRY_IMAGE}:latest"
   services:
     - name: docker:dind
       alias: docker
 
-run_benchmark: &run_benchmark
+.run_benchmark: &run_benchmark
   <<: *use_base_container
   script:
     - pip3 install -e .
@@ -14,7 +14,7 @@ run_benchmark: &run_benchmark
     paths:
       - benchmarks/seceval/eval/outputs/
       - benchmarks/cybermetric/outputs/
-    expire_in: 1 month
+    expire_in: 12 month
   tags:
     - p40
     - x86
@@ -22,7 +22,7 @@ run_benchmark: &run_benchmark
     - if: $CI_COMMIT_BRANCH
       when: on_success
 
-🛠️ benchmark test_eval:
+🛠️ benchmark test_seceval:
   <<: *run_benchmark
   variables:
     OLLAMA_API_BASE: "http://localhost:8000"