Config simplified: default block + per-bench overrides only (removed env/limit/judge/concurrency; max_input_tokens 128000)

Co-Authored-By: Claude <noreply@anthropic.com>

evalharness/config/dp4-nothink.yaml

@@ -1,196 +1,75 @@
-gpqa_diamond:
+default:
-  generation_config:
+  temperature: 0.0
-    temperature: 1.0
+  top_p: 1.0
-    top_p: 1.0
+  stream: true
-    stream: true
+  max_tokens: 32768
-    max_tokens: 8192
+
-hle:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
 aime24:
-  generation_config:
+  temperature: 1.0
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
   repeats: 12
+
 aime25:
-  generation_config:
+  temperature: 1.0
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
   repeats: 12
-mmlu_pro:
+
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
-simple_qa:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
-arc:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
-bbh:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-live_code_bench:
-  generation_config:
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-  dataset_args:
-    subset_list:
-    - release_v6
 aime26:
-  generation_config:
+  temperature: 1.0
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
   repeats: 12
+
 hmmt26:
-  generation_config:
+  temperature: 1.0
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
   repeats: 12
+
 imo_answerbench:
-  generation_config:
+  temperature: 1.0
-    temperature: 1.0
+
-    top_p: 1.0
+gpqa_diamond:
-    stream: true
+  temperature: 1.0
-    max_tokens: 32768
+  max_tokens: 8192
-drop:
+
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-hellaswag:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
 mmlu:
-  generation_config:
+  max_tokens: 8192
-    temperature: 0.0
+
-    top_p: 1.0
+mmlu_pro:
-    stream: true
+  max_tokens: 8192
-    max_tokens: 8192
+
-openai_mrcr:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
-bigcodebench:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-humaneval:
-  generation_config:
-    temperature: 1.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-gsm8k:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
-competition_math:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768
 cmmlu:
-  generation_config:
+  max_tokens: 8192
-    temperature: 0.0
+
-    top_p: 1.0
+arc:
-    stream: true
+  max_tokens: 8192
-    max_tokens: 8192
+
-trivia_qa:
+hellaswag:
-  generation_config:
+  max_tokens: 8192
-    temperature: 0.0
+
-    top_p: 1.0
-    stream: true
-    max_tokens: 8192
 winogrande:
-  generation_config:
+  max_tokens: 8192
-    temperature: 0.0
+
-    top_p: 1.0
+simple_qa:
-    stream: true
+  max_tokens: 8192
-    max_tokens: 8192
+
+trivia_qa:
+  max_tokens: 8192
+
+humaneval:
+  temperature: 1.0
+
+live_code_bench:
+  temperature: 1.0
+
 longbench_v2:
-  generation_config:
+  max_tokens: 8192
-    temperature: 0.0
+  max_input_tokens: 128000
-    top_p: 1.0
+
-    stream: true
+openai_mrcr:
-    max_tokens: 8192
+  max_tokens: 8192
-  dataset_args:
+  max_input_tokens: 128000
-    subset_list:
+
-    - short
-    - medium
-    - long
-tau2_bench:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 16384
-  dataset_args:
-    extra_params:
-      user_model: deepseek-v4-pro
-      api_key: sk-9ed86ef546ca47e3afa7c3b014dea268
-      api_base: https://api.deepseek.com/v1
-      generation_config:
-        temperature: 0.0
-        max_tokens: 4096
-  env: tau2_official
-  max_turns: 50
-general_fc:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 4096
 bfcl_v3:
-  generation_config:
+  max_tokens: 4096
-    temperature: 0.0
+
-    top_p: 1.0
+general_fc:
-    stream: true
+  max_tokens: 4096
-    max_tokens: 4096
+
-    parallel_tool_calls: true
+tau2_bench:
-  dataset_args:
+  max_tokens: 16384
-    extra_params:
-      is_fc_model: true
-      underscore_to_dot: true
-  env: bfcl_mock
-swe_bench_verified:
-  generation_config:
-    temperature: 0.0
-    top_p: 1.0
-    stream: true
-    max_tokens: 32768