diff --git a/doc/markdown/assertions.md b/doc/markdown/assertions.md
index 555611d..8814668 100644
--- a/doc/markdown/assertions.md
+++ b/doc/markdown/assertions.md
@@ -44,7 +44,7 @@
 REQUIRE_FALSE(thisReturnsFalse());
 ```
 
-- Using the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option can make compilation of asserts up to [**XX-XX%**](benchmarks.md#cost-of-an-assertion-macro) faster!
+- Using the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option can make compilation of asserts up to [**31-63%**](benchmarks.md#cost-of-an-assertion-macro) faster!
 - These asserts also have a ```_MESSAGE``` form - like ```CHECK_MESSAGE(expression, message)``` which is basically a code block ```{}``` with a scoped [**```INFO()```**](logging.md#info) logging macro together with the ```CHECK``` macro - that way the message will be relevant only to that assert. The binary/unary asserts don't have this variation yet.
 
 Examples:
@@ -63,7 +63,7 @@
 
 These asserts don't use templates to decompose the comparison expressions for the left and right parts.
 
-These have the same guarantees as the expression decomposing ones but [**XX%-XX% faster**](benchmarks.md#cost-of-an-assertion-macro) for compilation.
+These have the same guarantees as the expression decomposing ones but [**57-68% faster**](benchmarks.md#cost-of-an-assertion-macro) for compilation.
 
 ```<LEVEL>``` is one of 3 possible: ```REQUIRE```/```CHECK```/```WARN```.
 
@@ -76,7 +76,7 @@
 - ```<LEVEL>_UNARY(expr)``` - same as ```<LEVEL>(expr)```
 - ```<LEVEL>_UNARY_FALSE(expr)``` - same as ```<LEVEL>_FALSE(expr)```
 
-Using the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option can make compilation of asserts up to [**XX-XX%**](benchmarks.md#cost-of-an-assertion-macro) faster!
+Using the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option can make the binary asserts to compile up to [**84-91%**](benchmarks.md#cost-of-an-assertion-macro) faster!
 
 ## Exceptions
 
diff --git a/doc/markdown/benchmarks.md b/doc/markdown/benchmarks.md
index 1d09128..dd192d8 100644
--- a/doc/markdown/benchmarks.md
+++ b/doc/markdown/benchmarks.md
@@ -139,15 +139,15 @@
 **doctest**:
 
 - is between 0 and 8 times faster than [**Catch**](https://github.com/philsquared/Catch) when using normal expression decomposing ```CHECK(a==b)``` asserts
-- asserts of the form ```CHECK_EQ(a,b)``` with no expression decomposition - around 31%-63% faster than ```CHECK(a==b)```
-- the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) identifier which makes the fast assertions even faster by another 55-78%
-- TODO: mention the super fast mode with normal asserts vs the fast compile option of catch
-- using the [**```DOCTEST_CONFIG_DISABLE```**](configuration.md#doctest_config_disable) identifier the assertions just disappear as if they were never written - even lower than the baseline (because most of the implementation is also gone)
+- asserts of the form ```CHECK_EQ(a,b)``` with no expression decomposition - around 31-63% faster than ```CHECK(a==b)```
+- the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) identifier makes the normal asserts faster by 57-68%
+- the [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) identifier makes the binary asserts even faster by another 84-91%
+- using the [**```DOCTEST_CONFIG_DISABLE```**](configuration.md#doctest_config_disable) identifier the asserts just disappear as if they were never written - even lower than the baseline (because most of the implementation is also gone)
 
 [**Catch**](https://github.com/philsquared/Catch):
 
-- using [**```CATCH_CONFIG_FAST_COMPILE```**](https://github.com/philsquared/Catch/blob/master/docs/configuration.md#catch_config_fast_compile) results in 10%-30% faster build times for asserts (and in one case 73%).
-- using the **```CATCH_CONFIG_DISABLE```** identifier provides the same great benefits for assertion macros as the doctest version ([**```DOCTEST_CONFIG_DISABLE```**](configuration.md#doctest_config_disable)) - unlike in the case for the header cost
+- using [**```CATCH_CONFIG_FAST_COMPILE```**](https://github.com/philsquared/Catch/blob/master/docs/configuration.md#catch_config_fast_compile) results in 10-30% faster build times for asserts (and in one case 73%).
+- using the **```CATCH_CONFIG_DISABLE```** identifier provides the same great benefits for assert macros as the doctest version ([**```DOCTEST_CONFIG_DISABLE```**](configuration.md#doctest_config_disable)) - but not for the header cost
 
 ## Runtime benchmarks
 
diff --git a/doc/markdown/faq.md b/doc/markdown/faq.md
index b4a9964..eafa2a0 100644
--- a/doc/markdown/faq.md
+++ b/doc/markdown/faq.md
@@ -59,7 +59,7 @@
 
 ### How to get the best compile-time performance with the framework?
 
-The [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option yelds the [**fastest possible**](benchmarks.md#cost-of-an-assertion-macro) compile times (up to XX-XX%). Also the expression-decomposing template machinery can be skipped by using the [**binary**](assertions.md#binary-and-unary-asserts) asserts.
+The [**```DOCTEST_CONFIG_SUPER_FAST_ASSERTS```**](configuration.md#doctest_config_super_fast_asserts) config option yelds the [**fastest possible**](benchmarks.md#cost-of-an-assertion-macro) compile times (up to 31-91%). Also the expression-decomposing template machinery can be skipped by using the [**binary**](assertions.md#binary-and-unary-asserts) asserts.
 
 There are only 2 tiny drawbacks of using this config option:
 
diff --git a/doc/markdown/features.md b/doc/markdown/features.md
index 02f2c94..049c44a 100644
--- a/doc/markdown/features.md
+++ b/doc/markdown/features.md
@@ -32,7 +32,7 @@
 	- all tests built and ran in **Debug**/**Release** modes
 	- all tests ran through **valgrind** under **Linux** (sadly [not under OSX](https://github.com/onqtam/doctest/issues/11))
 	- all tests ran through **address**, **UB** and **thread** sanitizers under **Linux**/**OSX**
-	- tests are ran in more than **168** different configurations on UNIX (Linux + OSX) on **travis** CI
+	- tests are ran in more than **140** different configurations on UNIX (Linux + OSX) on **travis** CI
 	- tests are ran in a total of **10** different configurations on Windows on **appveyor** CI
 
 ## Other features:
diff --git a/scripts/data/benchmarks/asserts.png b/scripts/data/benchmarks/asserts.png
index 71e8ec9..a19bb22 100644
--- a/scripts/data/benchmarks/asserts.png
+++ b/scripts/data/benchmarks/asserts.png
Binary files differ