初始化项目，由ModelHub XC社区提供模型

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

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 351,
+      "gen_seconds": 32,
+      "symbolic_correct": 77.48294162244125,
+      "no_answer": 1.7437452615617892
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 663,
+      "gen_seconds": 117,
+      "symbolic_correct": 54.56,
+      "no_answer": 6.94
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 105,
+      "gen_seconds": 26,
+      "passing_base_tests": 48.170731707317074,
+      "passing_plus_tests": 42.073170731707314
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 13.37166209767489,
+      "prompt_strict_accuracy": 10.54421768707483,
+      "instruction_strict_accuracy": 11.641791044776118,
+      "prompt_loose_accuracy": 14.285714285714285,
+      "instruction_loose_accuracy": 17.01492537313433,
+      "num_entries": 294,
+      "avg_tokens": 429,
+      "gen_seconds": 27
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 54.65005075422103,
+      "prompt_strict_accuracy": 47.874306839186694,
+      "instruction_strict_accuracy": 58.39328537170264,
+      "prompt_loose_accuracy": 50.46210720887245,
+      "instruction_loose_accuracy": 61.87050359712231,
+      "num_entries": 541,
+      "avg_tokens": 472,
+      "gen_seconds": 30
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 67,
+      "gen_seconds": 27,
+      "passing_base_tests": 63.22751322751323,
+      "passing_plus_tests": 54.4973544973545
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 641,
+      "gen_seconds": 27,
+      "symbolic_correct": 19.11764705882353,
+      "no_answer": 4.411764705882353
+    }
+  }
+}