diff --git a/src/amd/ci/angle-radv-stoney-aco-fails.txt b/src/amd/ci/angle-radv-stoney-aco-fails.txt
index 396e77ac7d5..3a77ad51bbe 100644
--- a/src/amd/ci/angle-radv-stoney-aco-fails.txt
+++ b/src/amd/ci/angle-radv-stoney-aco-fails.txt
@@ -8,12 +8,6 @@
 KHR-GLES31.core.geometry_shader.rendering.rendering.triangles_with_adjacency_input_line_strip_output_triangle_strip_adjacency_drawcall,Fail
 KHR-GLES31.core.geometry_shader.rendering.rendering.triangles_with_adjacency_input_triangle_strip_output_triangle_strip_adjacency_drawcall,Fail
 
-# ANGLE passes depthBiasConstantFactor directly to GlobalDepthOffsetConstant, while zink multiplies by 2.0.
-# radeonsi has an extra 2.0 factor in the 16-bit depth case vs 24-bit, which radv doesn't have.
-# I expect this is a radv bug due to missing VK CTS coverage:
-# https://gitlab.khronos.org/Tracker/vk-gl-cts/-/issues/4169
-dEQP-GLES3.functional.polygon_offset.fixed16_render_with_units,Fail
-
 # Failure in later miplevels, occasionally flaky
 dEQP-GLES3.functional.texture.specification.teximage2d_depth.depth_component24,Fail
 dEQP-GLES3.functional.texture.specification.teximage2d_depth.depth24_stencil8,Fail