diff --git a/docs/user_guide.md b/docs/user_guide.md
index 95f57b3e..d22a9069 100644
--- a/docs/user_guide.md
+++ b/docs/user_guide.md
@@ -28,6 +28,8 @@
 
 [Templated Benchmarks](#templated-benchmarks)
 
+[Templated Benchmarks that take arguments](#templated-benchmarks-with-arguments)
+
 [Fixtures](#fixtures)
 
 [Custom Counters](#custom-counters)
@@ -574,6 +576,30 @@ Three macros are provided for adding benchmark templates.
 #define BENCHMARK_TEMPLATE2(func, arg1, arg2)
 ```
 
+<a name="templated-benchmarks-with-arguments" />
+
+## Templated Benchmarks that take arguments
+
+Sometimes there is a need to template benchmarks, and provide arguments to them.
+
+```c++
+template <class Q> void BM_Sequential_With_Step(benchmark::State& state, int step) {
+  Q q;
+  typename Q::value_type v;
+  for (auto _ : state) {
+    for (int i = state.range(0); i-=step; )
+      q.push(v);
+    for (int e = state.range(0); e-=step; )
+      q.Wait(&v);
+  }
+  // actually messages, not bytes:
+  state.SetBytesProcessed(
+      static_cast<int64_t>(state.iterations())*state.range(0));
+}
+
+BENCHMARK_TEMPLATE1_CAPTURE(BM_Sequential, WaitQueue<int>, Step1, 1)->Range(1<<0, 1<<10);
+```
+
 <a name="fixtures" />
 
 ## Fixtures
diff --git a/include/benchmark/benchmark.h b/include/benchmark/benchmark.h
index 25c3eef7..5a1eef89 100644
--- a/include/benchmark/benchmark.h
+++ b/include/benchmark/benchmark.h
@@ -1523,7 +1523,7 @@ class Fixture : public internal::Benchmark {
 // /* Registers a benchmark named "BM_takes_args/int_string_test` */
 // BENCHMARK_CAPTURE(BM_takes_args, int_string_test, 42, std::string("abc"));
 #define BENCHMARK_CAPTURE(func, test_case_name, ...)     \
-  BENCHMARK_PRIVATE_DECLARE(func) =                      \
+  BENCHMARK_PRIVATE_DECLARE(_benchmark_) =               \
       (::benchmark::internal::RegisterBenchmarkInternal( \
           new ::benchmark::internal::FunctionBenchmark(  \
               #func "/" #test_case_name,                 \
@@ -1560,6 +1560,31 @@ class Fixture : public internal::Benchmark {
 #define BENCHMARK_TEMPLATE(n, a) BENCHMARK_TEMPLATE1(n, a)
 #endif
 
+#ifdef BENCHMARK_HAS_CXX11
+// This will register a benchmark for a templatized function,
+// with the additional arguments specified by `...`.
+//
+// For example:
+//
+// template <typename T, class ...ExtraArgs>`
+// void BM_takes_args(benchmark::State& state, ExtraArgs&&... extra_args) {
+//  [...]
+//}
+// /* Registers a benchmark named "BM_takes_args<void>/int_string_test` */
+// BENCHMARK_TEMPLATE1_CAPTURE(BM_takes_args, void, int_string_test, 42,
+//                             std::string("abc"));
+#define BENCHMARK_TEMPLATE1_CAPTURE(func, a, test_case_name, ...) \
+  BENCHMARK_CAPTURE(func<a>, test_case_name, __VA_ARGS__)
+
+#define BENCHMARK_TEMPLATE2_CAPTURE(func, a, b, test_case_name, ...) \
+  BENCHMARK_PRIVATE_DECLARE(func) =                                  \
+      (::benchmark::internal::RegisterBenchmarkInternal(             \
+          new ::benchmark::internal::FunctionBenchmark(              \
+              #func "<" #a "," #b ">"                                \
+                    "/" #test_case_name,                             \
+              [](::benchmark::State& st) { func<a, b>(st, __VA_ARGS__); })))
+#endif  // BENCHMARK_HAS_CXX11
+
 #define BENCHMARK_PRIVATE_DECLARE_F(BaseClass, Method)          \
   class BaseClass##_##Method##_Benchmark : public BaseClass {   \
    public:                                                      \
diff --git a/test/benchmark_test.cc b/test/benchmark_test.cc
index 94590d5e..8b14017d 100644
--- a/test/benchmark_test.cc
+++ b/test/benchmark_test.cc
@@ -16,6 +16,7 @@
 #include <sstream>
 #include <string>
 #include <thread>
+#include <type_traits>
 #include <utility>
 #include <vector>
 
@@ -226,6 +227,31 @@ void BM_non_template_args(benchmark::State& state, int, double) {
 }
 BENCHMARK_CAPTURE(BM_non_template_args, basic_test, 0, 0);
 
+template <class T, class U, class... ExtraArgs>
+void BM_template2_capture(benchmark::State& state, ExtraArgs&&... extra_args) {
+  static_assert(std::is_same<T, void>::value, "");
+  static_assert(std::is_same<U, char*>::value, "");
+  static_assert(std::is_same<ExtraArgs..., unsigned int>::value, "");
+  unsigned int dummy[sizeof...(ExtraArgs)] = {extra_args...};
+  assert(dummy[0] == 42);
+  for (auto _ : state) {
+  }
+}
+BENCHMARK_TEMPLATE2_CAPTURE(BM_template2_capture, void, char*, foo, 42U);
+BENCHMARK_CAPTURE((BM_template2_capture<void, char*>), foo, 42U);
+
+template <class T, class... ExtraArgs>
+void BM_template1_capture(benchmark::State& state, ExtraArgs&&... extra_args) {
+  static_assert(std::is_same<T, void>::value, "");
+  static_assert(std::is_same<ExtraArgs..., unsigned long>::value, "");
+  unsigned long dummy[sizeof...(ExtraArgs)] = {extra_args...};
+  assert(dummy[0] == 24);
+  for (auto _ : state) {
+  }
+}
+BENCHMARK_TEMPLATE1_CAPTURE(BM_template1_capture, void, foo, 24UL);
+BENCHMARK_CAPTURE(BM_template1_capture<void>, foo, 24UL);
+
 #endif  // BENCHMARK_HAS_CXX11
 
 static void BM_DenseThreadRanges(benchmark::State& st) {