diff --git a/eval/README.md b/eval/README.md
index c5dd3ce3..8146a8f7 100644
--- a/eval/README.md
+++ b/eval/README.md
@@ -34,7 +34,7 @@ export OPENROUTER_API_KEY=your-api-key
 ```
 
 
-4. Prepare your dataset configuration in YAML format (see examples in `yaml/algorithmic.yaml` or `yaml/logic.yaml`):
+4. Prepare your dataset configuration in YAML format (see examples in `yaml/<model_name>/algorithmic.yaml` e.g `yaml/r1/algorithmic.yaml`):
 ```yaml
 model: model-name
 category: category-name
@@ -130,8 +130,9 @@ python eval.py --yaml <path-to yaml file>
 ```
 e.g
 ```
-python eval.py --yaml yaml/algorithmic.yaml
+python eval.py --yaml yaml/r1/algorithmic.yaml
 ```
+To run r1 evaluations on algorithmic.yaml
 
 
 The results of individual model on a dataset will be stored in a new folder in the directory E.g `r1/algorithmic/proposition_logic.json`
diff --git a/eval/yaml/anthropic/algorithmic.yaml b/eval/yaml/anthropic/algorithmic.yaml
new file mode 100644
index 00000000..bd2e1ccd
--- /dev/null
+++ b/eval/yaml/anthropic/algorithmic.yaml
@@ -0,0 +1,31 @@
+model: anthropic/claude-3.5-sonnet
+category: algorithmic
+provider: Anthropic
+datasets:
+  -  count_primes
+  -  game_of_life
+  -  graph_color
+  -  group_anagrams
+  -  isomorphic_strings
+  -  letter_counting
+  -  letter_jumble
+  -  manipulate_matrix
+  -  number_filtering
+  -  number_sorting
+  -  palindrome
+  -  pool_matrix
+  -  ransom_note
+  -  rotate_matrix
+  -  sentence_reordering
+  -  spell_backward
+  -  spiral_matrix
+  -  string_insertion
+  -  string_manipulation
+  -  string_synthesis
+  -  word_ladder
+  -  word_sequence_reversal
+  -  word_sorting
+eval_dir: eval/r1
+dataset_size: 50
+dataset_seed: 45
+developer_role: system
diff --git a/eval/yaml/algebra.yaml b/eval/yaml/r1/algebra.yaml
similarity index 100%
rename from eval/yaml/algebra.yaml
rename to eval/yaml/r1/algebra.yaml
diff --git a/eval/yaml/algorithmic.yaml b/eval/yaml/r1/algorithmic.yaml
similarity index 100%
rename from eval/yaml/algorithmic.yaml
rename to eval/yaml/r1/algorithmic.yaml
diff --git a/eval/yaml/cognition.yaml b/eval/yaml/r1/cognition.yaml
similarity index 100%
rename from eval/yaml/cognition.yaml
rename to eval/yaml/r1/cognition.yaml
diff --git a/eval/yaml/r1/logic.yaml b/eval/yaml/r1/logic.yaml
new file mode 100644
index 00000000..400c4ff3
--- /dev/null
+++ b/eval/yaml/r1/logic.yaml
@@ -0,0 +1,11 @@
+model: deepseek/deepseek-r1
+category: logic
+datasets:
+  - propositional_logic
+  - self_reference
+  - syllogism
+  - zebra_puzzles
+eval_dir: eval/r1
+dataset_size: 50
+dataset_seed: 42
+developer_role: system