Quick test (only unpack) with LibRaw compiled via make -f Makefile.dist (so no openmp), three files with different encoding:

0.22.0:

$ time ./bin/unprocessed_raw ~/tt/GFX100II/GFX100_II_1*RAF
Processing file /home/lexa/tt/GFX100II/GFX100_II_14bits_uncompressed_4x3.RAF
Image size: 11662x8746
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_14bits_uncompressed_4x3.RAF.pgm
Processing file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossless_4x3.RAF
Image size: 11662x8746
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossless_4x3.RAF.pgm
Processing file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossy_4x3.RAF
Image size: 11662x8746
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossy_4x3.RAF.pgm

real    0m22,756s
user    0m21,958s
sys     0m0,783s

0.21.5:

$ time ./bin/unprocessed_raw ~/tt/GFX100II/GFX100_II_1*RAF
Processing file /home/lexa/tt/GFX100II/GFX100_II_14bits_uncompressed_4x3.RAF
Image size: 11662x8752
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_14bits_uncompressed_4x3.RAF.pgm
Processing file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossless_4x3.RAF
Image size: 11662x8752
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossless_4x3.RAF.pgm
Processing file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossy_4x3.RAF
Image size: 11662x8752
Raw size: 11808x8754
Margins: top=2, left=0
Unpacked....
Stored to file /home/lexa/tt/GFX100II/GFX100_II_16bits_lossy_4x3.RAF.pgm

real    0m22,798s
user    0m21,929s
sys     0m0,854s

CPU: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz (2200.21-MHz K8-class CPU)
Storage: fast SSD (nvme)

So, please provide test file you use for benchmarking for more in-depth study.