diff --git a/recipes/glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m/recipe.yaml b/recipes/glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m/recipe.yaml
index 82ec05ee0..ff13c0f1d 100644
--- a/recipes/glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m/recipe.yaml
+++ b/recipes/glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m/recipe.yaml
@@ -88,17 +88,17 @@ performance:
       context_len: 131072
       concurrency: 1
       decode_tok_s: 72.3
-      notes: 'code decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+0 because the table keys one row per (context_len, concurrency)'
+      notes: 'code decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md)'
     -
-      context_len: 151552
+      context_len: 141312
       concurrency: 1
       decode_tok_s: 38.3
-      notes: 'prose decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+20480 because the table keys one row per (context_len, concurrency)'
+      notes: 'prose decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+10240 because the table keys one row per (context_len, concurrency)'
     -
-      context_len: 172032
+      context_len: 151552
       concurrency: 1
       decode_tok_s: 91.7
-      notes: 'structured decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+40960 because the table keys one row per (context_len, concurrency)'
+      notes: 'structured decode c1, median of 3 (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+20480 because the table keys one row per (context_len, concurrency)'
     -
       context_len: 8192
       concurrency: 1
@@ -125,10 +125,10 @@ performance:
       ttft_ms: 3537
       notes: 'RigMark staggered arrivals prefill-first: newcomer TTFT at c4, 32K depth (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md)'
     -
-      context_len: 131072
+      context_len: 172032
       concurrency: 1
       decode_tok_s: 47.0
-      notes: 'RigMark short code c1 aggregate end-to-end (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md)'
+      notes: 'RigMark short code c1 aggregate end-to-end (RigMark (40fabcaf fork w/ staggered-arrival suite, seed 20260905, reasoning_effort low, thinking on), 8x128k profile per bench/RIGMARK.md); context_len is the tuple marker 131072+40960 because the table keys one row per (context_len, concurrency)'
     -
       context_len: 131072
       concurrency: 4
@@ -140,10 +140,10 @@ performance:
       decode_tok_s: 45.57
       notes: 'single-stream prose decode, 12 prompts x 256 tokens (production settings: 4x1m profile, 0.91, display carveout, KV shard, disk prefix cache 48 GB; thinking off, greedy, raw/multi-rc4_on.json)'
     -
-      context_len: 1069056
+      context_len: 1130496
       concurrency: 1
       decode_tok_s: 64.91
-      notes: 'single-stream code decode, 12 prompts x 256 tokens (production settings: 4x1m profile, 0.91, display carveout, KV shard, disk prefix cache 48 GB; thinking off, greedy, raw/multi-rc4_on.json); context_len is the tuple marker 1048576+20480 because the table keys one row per (context_len, concurrency)'
+      notes: 'single-stream code decode, 12 prompts x 256 tokens (production settings: 4x1m profile, 0.91, display carveout, KV shard, disk prefix cache 48 GB; thinking off, greedy, raw/multi-rc4_on.json); context_len is the tuple marker 1048576+81920 because the table keys one row per (context_len, concurrency)'
 artifacts:
   -
     kind: model_weights