Add eval results

.eval_results/gpqa_diamond.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 84.3
+  date: '2026-04-02'
+  source:
+    url: https://huggingface.co/google/gemma-4-31B-it
+    name: Model Card
+    user: merve

.eval_results/hle.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 19.5
+  date: '2026-04-02'
+  source:
+    url: https://huggingface.co/google/gemma-4-31B-it
+    name: Model Card
+    user: merve

.eval_results/hle_with_tools.yaml

@@ -0,0 +1,10 @@
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 26.5
+  date: '2026-04-02'
+  source:
+    url: https://huggingface.co/google/gemma-4-31B-it
+    name: Model Card
+    user: merve
+  notes: "With search"

.eval_results/mmlu_pro.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 85.2
+  date: '2026-04-02'
+  source:
+    url: https://huggingface.co/google/gemma-4-31B-it
+    name: Model Card
+    user: merve