初始化项目，由ModelHub XC社区提供模型

Model: seopbo/rlvrcodemathif-qwen2.5-1.5b
Source: Original Platform

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 339,
+      "gen_seconds": 75,
+      "symbolic_correct": 77.93783169067476,
+      "no_answer": 0.9097801364670205
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 648,
+      "gen_seconds": 164,
+      "symbolic_correct": 55.36,
+      "no_answer": 5.88
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 87,
+      "gen_seconds": 41,
+      "passing_base_tests": 54.26829268292683,
+      "passing_plus_tests": 46.34146341463415
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 20.429739059803026,
+      "prompt_strict_accuracy": 17.687074829931973,
+      "instruction_strict_accuracy": 19.701492537313435,
+      "prompt_loose_accuracy": 20.74829931972789,
+      "instruction_loose_accuracy": 23.582089552238806,
+      "num_entries": 294,
+      "avg_tokens": 423,
+      "gen_seconds": 51
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 71.13392465325336,
+      "prompt_strict_accuracy": 65.06469500924214,
+      "instruction_strict_accuracy": 74.10071942446042,
+      "prompt_loose_accuracy": 68.39186691312385,
+      "instruction_loose_accuracy": 76.97841726618705,
+      "num_entries": 541,
+      "avg_tokens": 480,
+      "gen_seconds": 58
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 60,
+      "gen_seconds": 51,
+      "passing_base_tests": 67.46031746031746,
+      "passing_plus_tests": 57.407407407407405
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 676,
+      "gen_seconds": 58,
+      "symbolic_correct": 17.279411764705884,
+      "no_answer": 6.985294117647059
+    }
+  }
+}