We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 1c4f961 commit 3d49bd8Copy full SHA for 3d49bd8
scripts/run_evaluate_multiple_runs_xbench-ds.sh
@@ -6,7 +6,7 @@
6
7
# Configuration parameters
8
NUM_RUNS=3
9
-AGENT_SET="agent_quickstart_1"
+AGENT_SET="agent_xbench-ds"
10
BENCHMARK_NAME="xbench-ds"
11
MAX_CONCURRENT=5
12
export CHINESE_CONTEXT="true"
@@ -87,4 +87,4 @@ uv run utils/util_llm_parallel_thinking.py \
87
88
echo "=========================================="
89
echo "Parallel thinking post-processing completed!"
90
-echo "=========================================="
+echo "=========================================="
0 commit comments