diff --git a/.github/workflows/cicd-main.yml b/.github/workflows/cicd-main.yml
index c38cc2dd87..a5d2c7126b 100644
--- a/.github/workflows/cicd-main.yml
+++ b/.github/workflows/cicd-main.yml
@@ -172,6 +172,7 @@ jobs:
           time uv run --no-sync bash ./tests/functional/grpo.sh
           time uv run --no-sync bash ./tests/functional/grpo_multiturn.sh
           time uv run --no-sync bash ./tests/functional/dpo.sh
+          time uv run --no-sync bash ./tests/functional/eval.sh
         else
           echo Skipping functional tests for level ${{ needs.pre-flight.outputs.test_level }}
         fi
diff --git a/tests/functional/eval.sh b/tests/functional/eval.sh
new file mode 100644
index 0000000000..d434265e2e
--- /dev/null
+++ b/tests/functional/eval.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd)
+PROJECT_ROOT=$(realpath $SCRIPT_DIR/../..)
+# Mark the current repo as safe, since wandb fetches metadata about the repo
+git config --global --add safe.directory $PROJECT_ROOT
+
+set -eou pipefail
+
+EXP_NAME=$(basename $0 .sh)
+EXP_DIR=$SCRIPT_DIR/$EXP_NAME
+LOG_DIR=$EXP_DIR/logs
+JSON_METRICS=$EXP_DIR/metrics.json
+RUN_LOG=$EXP_DIR/run.log
+export UV_CACHE_DIR=${UV_CACHE_DIR:-$PROJECT_ROOT/uv_cache}
+export PYTHONPATH=${PROJECT_ROOT}:${PYTHONPATH:-}
+
+rm -rf $EXP_DIR $LOG_DIR
+mkdir -p $EXP_DIR $LOG_DIR
+
+cd $PROJECT_ROOT
+uv run $PROJECT_ROOT/examples/run_eval.py \
+    cluster.gpus_per_node=2 \
+    $@ \
+    2>&1 | tee $RUN_LOG
+
+cat $RUN_LOG | grep "score=" | sed 's/.*score=\([^ ]*\).*/{"score": \1}/' > $JSON_METRICS
+
+uv run tests/check_metrics.py $JSON_METRICS \
+  'data["score"] == 0.1' \