111

ReliableMath.tsv

@@ -7,5 +7,8 @@ deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	32	Reliable	0.551	0.001	0.684	0.000	5.0
 deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	14	Reliable	0.547	0.000	0.629	0.000	6.23k	0.465	0.001	11.00k
 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	7	Reliable	0.289	0.000	0.575	0.000	6.24k	0.003	0.000	6.60k
 deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	1.5	Reliable	0.198	0.000	0.396	0.000	9.37k	0.000	0.000	9.70k
+Qwen/Qwen3-235B-A22B	235	Reliable	0.621	0.001	0.767	0.000	5.64k	0.475	0.003	5.60k
+Qwen/Qwen3-32B	32	Reliable	0.545   	0.000	0.764	0.000	5.88k	0.326	0.000	6.00k
+Qwen/Qwen3-14B	14	Reliable	0.573 	0.002	0.748	0.003	5.87k	0.399	0.000 	6.10k
 Qwen/Qwen2.5-Math-7B-Instruct	7	Reliable	0.266	0.000	0.505	0.000	0.82k	0.027	0.000	0.90k
 Qwen/Qwen2.5-Math-1.5B-Instruct	1.5	Reliable	0.218	0.000	0.422	0.000	0.74k	0.015	0.000	0.80k

app.py

@@ -26,7 +26,7 @@ df["Size_Display"] = df["Size"].apply(
 
 model_types = {
     "reasoning": ["deepseek-ai/DeepSeek-R1", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "OpenAI/o3-mini"],
-    "instruction": ["OpenAI/GPT-4o", "deepseek-ai/DeepSeek-V3", "Qwen/Qwen2.5-Math-1.5B-Instruct", "Qwen/Qwen2.5-Math-7B-Instruct"]
+    "instruction": ["OpenAI/GPT-4o", "deepseek-ai/DeepSeek-V3", "Qwen/Qwen2.5-Math-1.5B-Instruct", "Qwen/Qwen2.5-Math-7B-Instruct", "Qwen/Qwen3-235B-A22B", "Qwen/Qwen3-32B", "Qwen/Qwen3-14B"]
 }
 
 # Add size category for filtering