diff --git a/.github/scripts/oc_score_baseline_fullbench.yaml b/.github/scripts/oc_score_baseline_fullbench.yaml
index 966aeed2..471c6602 100644
--- a/.github/scripts/oc_score_baseline_fullbench.yaml
+++ b/.github/scripts/oc_score_baseline_fullbench.yaml
@@ -39,15 +39,15 @@ internlm2_5-7b-chat-hf_fullbench:
         college_knowledge_naive_average: 87.5
     subjective:
         alignment_bench_v1_1_总分: 0.66
-        alpaca_eval_total: 0
-        arenahard_score: 50
+        alpaca_eval_total: 20.00
+        arenahard_score: 56.82
         Followbench_naive_average: 1
         CompassArena_naive_average: 43
-        mtbench101_avg: 7.8
-        wildbench_average: -15.56
-        simpleqa_accuracy_given_attempted: 0
-        chinese_simpleqa_given_attempted_accuracy: 1
-        alignment_bench_v1_1_专业能力: 8.00
+        mtbench101_avg: 7.60
+        wildbench_average: -14.58
+        simpleqa_accuracy_given_attempted: 1.00
+        chinese_simpleqa_given_attempted_accuracy: 0.90
+        alignment_bench_v1_1_专业能力: 7.90
         alignment_bench_v1_1_数学计算: 0
         alignment_bench_v1_1_基本任务: 0
         alignment_bench_v1_1_逻辑推理: 0
@@ -55,11 +55,11 @@ internlm2_5-7b-chat-hf_fullbench:
         alignment_bench_v1_1_文本写作: 0
         alignment_bench_v1_1_角色扮演: 0
         alignment_bench_v1_1_综合问答: 0
-        alpaca_eval_helpful_base: 0
+        alpaca_eval_helpful_base: 20.00
         compassarena_language_naive_average: 35
-        compassarena_knowledge_naive_average: 55
+        compassarena_knowledge_naive_average: 60.00
         compassarena_reason_v2_naive_average: 40
-        compassarena_math_v2_naive_average: 55
+        compassarena_math_v2_naive_average: 50.00
         compassarena_creationv2_zh_naive_average: 30
         followbench_llmeval_en_HSR_AVG: 1
         followbench_llmeval_en_SSR_AVG: 1
@@ -73,7 +73,7 @@ internlm2_5-7b-chat-hf_fullbench:
         followbench_llmeval_en_SSR_L3: 1
         followbench_llmeval_en_SSR_L4: 1
         followbench_llmeval_en_SSR_L5: 1
-        simpleqa_f1: 0
+        simpleqa_f1: 0.12
 
 internlm2_5-7b-chat-turbomind_fullbench:
     objective:
@@ -115,16 +115,16 @@ internlm2_5-7b-chat-turbomind_fullbench:
         college_naive_average: 12.50
         college_knowledge_naive_average: 87.5
     subjective:
-        alignment_bench_v1_1_总分: 0.66
-        alpaca_eval_total: 0
-        arenahard_score: 50
+        alignment_bench_v1_1_总分: 0.72
+        alpaca_eval_total: 20.00
+        arenahard_score: 55.77
         Followbench_naive_average: 1
-        CompassArena_naive_average: 40
-        mtbench101_avg: 8
-        wildbench_average: -6.81
-        simpleqa_accuracy_given_attempted: 0
+        CompassArena_naive_average: 39.00
+        mtbench101_avg: 7.90
+        wildbench_average: 0.00
+        simpleqa_accuracy_given_attempted: 1.00
         chinese_simpleqa_given_attempted_accuracy: 1
-        alignment_bench_v1_1_专业能力: 7.9
+        alignment_bench_v1_1_专业能力: 8.70
         alignment_bench_v1_1_数学计算: 0
         alignment_bench_v1_1_基本任务: 0
         alignment_bench_v1_1_逻辑推理: 0
@@ -132,12 +132,12 @@ internlm2_5-7b-chat-turbomind_fullbench:
         alignment_bench_v1_1_文本写作: 0
         alignment_bench_v1_1_角色扮演: 0
         alignment_bench_v1_1_综合问答: 0
-        alpaca_eval_helpful_base: 0
-        compassarena_language_naive_average: 35
-        compassarena_knowledge_naive_average: 45
-        compassarena_reason_v2_naive_average: 25
-        compassarena_math_v2_naive_average: 60
-        compassarena_creationv2_zh_naive_average: 35
+        alpaca_eval_helpful_base: 20.00
+        compassarena_language_naive_average: 25.00
+        compassarena_knowledge_naive_average: 55.00
+        compassarena_reason_v2_naive_average: 35.00
+        compassarena_math_v2_naive_average: 55.00
+        compassarena_creationv2_zh_naive_average: 25.00
         followbench_llmeval_en_HSR_AVG: 1
         followbench_llmeval_en_SSR_AVG: 1
         followbench_llmeval_en_HSR_L1: 1
@@ -150,7 +150,7 @@ internlm2_5-7b-chat-turbomind_fullbench:
         followbench_llmeval_en_SSR_L3: 1
         followbench_llmeval_en_SSR_L4: 1
         followbench_llmeval_en_SSR_L5: 1
-        simpleqa_f1: 0
+        simpleqa_f1: 0.12
 
 internlm2_5-7b-hf_fullbench:
     objective: