diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index f4570fd2c..7ab473b47 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -1917,6 +1917,31 @@ kimik2.5-int4-h200-vllm:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+minimaxm2.5-fp4-b200-vllm:
+  image: vllm/vllm-openai:v0.18.0
+  model: nvidia/MiniMax-M2.5-NVFP4
+  model-prefix: minimaxm2.5
+  runner: b200
+  precision: fp4
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 2, ep: 2, conc-start: 4, conc-end: 64 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 2, ep: 2, conc-start: 4, conc-end: 64 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 4, conc-start: 4, conc-end: 64 }
+    - { tp: 2, ep: 2, conc-start: 4, conc-end: 64 }
+
 kimik2.5-fp4-b200-vllm:
   image: vllm/vllm-openai:v0.17.0
   model: nvidia/Kimi-K2.5-NVFP4
diff --git a/benchmarks/single_node/minimaxm2.5_fp4_b200.sh b/benchmarks/single_node/minimaxm2.5_fp4_b200.sh
new file mode 100755
index 000000000..aa0c3868f
--- /dev/null
+++ b/benchmarks/single_node/minimaxm2.5_fp4_b200.sh
@@ -0,0 +1,77 @@
+#!/usr/bin/env bash
+
+source "$(dirname "$0")/../benchmark_lib.sh"
+
+check_env_vars \
+    MODEL \
+    TP \
+    CONC \
+    ISL \
+    OSL \
+    MAX_MODEL_LEN \
+    RANDOM_RANGE_RATIO \
+    RESULT_FILENAME
+
+if [[ -n "$SLURM_JOB_ID" ]]; then
+  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
+fi
+
+hf download "$MODEL"
+
+nvidia-smi
+
+export TORCH_CUDA_ARCH_LIST="10.0"
+export PYTHONNOUSERSITE=1
+
+SERVER_LOG=/workspace/server.log
+PORT=${PORT:-8888}
+
+# EP support: conditionally enable expert parallel based on EP_SIZE env var
+if [ "${EP_SIZE:-1}" -gt 1 ]; then
+  EP=" --enable-expert-parallel"
+else
+  EP=" "
+fi
+
+# Start GPU monitoring (power, temperature, clocks every second)
+start_gpu_monitor
+
+set -x
+vllm serve $MODEL --host 0.0.0.0 --port $PORT \
+--tensor-parallel-size=$TP \
+--gpu-memory-utilization 0.90 \
+--max-model-len $MAX_MODEL_LEN \
+--max-num-seqs $CONC \
+--no-enable-prefix-caching \
+--compilation_config.pass_config.fuse_allreduce_rms true \
+--trust-remote-code${EP} > $SERVER_LOG 2>&1 &
+
+SERVER_PID=$!
+
+# Wait for server to be ready
+wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
+
+pip install -q datasets pandas
+
+run_benchmark_serving \
+    --model "$MODEL" \
+    --port "$PORT" \
+    --backend vllm \
+    --input-len "$ISL" \
+    --output-len "$OSL" \
+    --random-range-ratio "$RANDOM_RANGE_RATIO" \
+    --num-prompts $(( CONC * 10 )) \
+    --max-concurrency "$CONC" \
+    --result-filename "$RESULT_FILENAME" \
+    --result-dir /workspace/ \
+    --trust-remote-code
+
+# After throughput, run evaluation only if RUN_EVAL is true
+if [ "${RUN_EVAL}" = "true" ]; then
+    run_eval --framework lm-eval --port "$PORT" --concurrent-requests $CONC
+    append_lm_eval_summary
+fi
+
+# Stop GPU monitoring
+stop_gpu_monitor
+set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 2648e746e..acc9fb634 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1,3 +1,11 @@
+- config-keys:
+    - minimaxm2.5-fp4-b200-vllm
+  description:
+    - "Add MiniMax M2.5 NVFP4 single-node B200 vLLM benchmark (TP4, TP2)"
+    - "Uses vllm/vllm-openai:v0.18.0 image with --no-enable-prefix-caching"
+    - "Concurrency 4-64, all three seq-len configs (1k1k, 1k8k, 8k1k)"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX
+
 - config-keys:
     - dsr1-fp8-b200-dynamo-trt
     - dsr1-fp8-h200-dynamo-trt