Update README.md

README.md

@@ -166,14 +166,14 @@ For further details, questions, or feedback, please email episteme.ai@proton.me
 
 ## Benchmark
 
-hf (pretrained=EpistemeAI/ReasoningCore-3B-R01), gen_kwargs: (None), limit: None, num_fewshot: 1, batch_size: 8
+hf (pretrained=EpistemeAI/ReasoningCore-3B-R01), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
 |    Tasks    |Version|Filter|n-shot| Metric |   |Value |   |Stderr|
 |-------------|------:|------|-----:|--------|---|-----:|---|-----:|
-|arc_challenge|      1|none  |     1|acc     |↑  |0.4113|±  |0.0144|
-|             |       |none  |     1|acc_norm|↑  |0.4548|±  |0.0146|
-|hellaswag    |      1|none  |     1|acc     |↑  |0.5103|±  |0.0050|
-|             |       |none  |     1|acc_norm|↑  |0.6965|±  |0.0046|
-|winogrande   |      1|none  |     1|acc     |↑  |0.6654|±  |0.0133|
+|arc_challenge|      1|none  |     5|acc     |↑  |0.4352|±  |0.0145|
+|             |       |none  |     5|acc_norm|↑  |0.4889|±  |0.0146|
+|hellaswag    |      1|none  |     5|acc     |↑  |0.5147|±  |0.0050|
+|             |       |none  |     5|acc_norm|↑  |0.7087|±  |0.0045|
+|winogrande   |      1|none  |     5|acc     |↑  |0.6811|±  |0.0131|
 
 
 # Uploaded  model