diff --git a/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.json b/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.json
index 6e72f050..bb815c19 100644
--- a/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.json
+++ b/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.json
@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-05-20T15:44:19.975Z",
+  "generatedAt": "2026-05-27T08:11:47.513Z",
   "runsPerModel": 1,
   "qualification": {
     "minimumAverageScore": 80,
@@ -25,8 +25,8 @@
       "runtimeTransportFailures": 0,
       "modelBehaviorFailures": 0,
       "harnessFailures": 0,
-      "p50DurationMs": 201184,
-      "p95DurationMs": 201184,
+      "p50DurationMs": 129420,
+      "p95DurationMs": 129420,
       "stagePassRates": {
         "launchBootstrap": {
           "passed": 1,
@@ -217,16 +217,16 @@
           "outcome": "passed",
           "failureCategory": "none",
           "primaryFailure": null,
-          "durationMs": 201184,
+          "durationMs": 129420,
           "hardFailure": false,
           "stageDurationsMs": {
-            "setup": 322,
-            "launchBootstrap": 44102,
-            "materializeTasks": 40,
-            "directReply": 20838,
-            "peerRelayAB": 41022,
-            "peerRelayBC": 47832,
-            "concurrentReplies": 29138,
+            "setup": 168,
+            "launchBootstrap": 31364,
+            "materializeTasks": 29,
+            "directReply": 15080,
+            "peerRelayAB": 31900,
+            "peerRelayBC": 29178,
+            "concurrentReplies": 20867,
             "hygiene": 1
           },
           "stageFailures": {},
@@ -253,7 +253,7 @@
             "latencyStable": true
           },
           "diagnostics": [
-            "runId=85e7ecb6-0767-4606-90d2-c926937b22f5"
+            "runId=37f103a7-cae5-4d48-b578-56cbabb466d9"
           ]
         }
       ]
diff --git a/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.md b/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.md
index 0c4f989e..51f7194a 100644
--- a/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.md
+++ b/test-results/opencode-semantic-model-gauntlet/model-gauntlet-results.md
@@ -1,6 +1,6 @@
 # OpenCode Model Gauntlet Results
 
-Generated: 2026-05-20T15:44:19.975Z
+Generated: 2026-05-27T08:11:47.513Z
 
 Runs per model: 1
 Recommended threshold: average >= 80, successful runs >= 1, consistency >= 85, hard failures = 0
@@ -13,7 +13,7 @@ Scoring weights: launchBootstrap=15, directReply=10, peerRelayAB=15, peerRelayBC
 
 | Model | Verdict | Confidence | Readiness | Consistency | Score Spread | Behavior Avg | Overall Avg | Counted | Pass Runs | Weakest Stage | Weakest TaskRef | Dominant Failure | Blockers | Provider Infra | Runtime Transport | Model Fails | Protocol Runs | p50 | p95 |
 | --- | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | --- | --- | --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
-| `opencode/big-pickle` | Recommended | low | 100 | 100 | 0 | 100 | 100 | 1/1 | 1/1 | cleanTranscript 1/1 (100%) | concurrentBob 1/1 (100%) | none | - | 0 | 0 | 0 | 0 | 201184ms | 201184ms |
+| `opencode/big-pickle` | Recommended | low | 100 | 100 | 0 | 100 | 100 | 1/1 | 1/1 | cleanTranscript 1/1 (100%) | concurrentBob 1/1 (100%) | none | - | 0 | 0 | 0 | 0 | 129420ms | 129420ms |
 
 ## opencode/big-pickle
 
@@ -33,5 +33,5 @@ Protocol totals: badMessages=0, duplicateOrMissingTokens=0, affectedRuns=0.
 
 | Run | Outcome | Category | Score | Counted | Duration | Failed Stages | Slowest Stage | TaskRefs | Protocol | Diagnostics |
 | ---: | --- | --- | ---: | --- | ---: | --- | --- | --- | --- | --- |
-| 1 | passed | none | 100 | yes | 201184ms | - | peerRelayBC:47832ms | directReply:ok, peerRelayAB:ok, peerRelayBC:ok, concurrentBob:ok, concurrentTom:ok | - | runId=85e7ecb6-0767-4606-90d2-c926937b22f5 |
+| 1 | passed | none | 100 | yes | 129420ms | - | peerRelayAB:31900ms | directReply:ok, peerRelayAB:ok, peerRelayBC:ok, concurrentBob:ok, concurrentTom:ok | - | runId=37f103a7-cae5-4d48-b578-56cbabb466d9 |
 
diff --git a/test-results/opencode-semantic-model-matrix/report-1779869494489.json b/test-results/opencode-semantic-model-matrix/report-1779869494489.json
new file mode 100644
index 00000000..1e1f1670
--- /dev/null
+++ b/test-results/opencode-semantic-model-matrix/report-1779869494489.json
@@ -0,0 +1,24 @@
+{
+  "generatedAt": "2026-05-27T08:11:34.489Z",
+  "models": [
+    {
+      "model": "opencode/big-pickle",
+      "passed": true,
+      "score": 100,
+      "durationMs": 86233,
+      "stages": {
+        "launchBootstrap": true,
+        "directReply": true,
+        "peerRelay": true,
+        "taskRefs": true,
+        "longPrompt": true,
+        "latencyStable": true
+      },
+      "diagnostics": [
+        "runId=5a90cf2a-d00e-4e26-a514-5efecf1914af",
+        "directDelivery={\"delivered\":true,\"accepted\":true,\"responsePending\":false,\"responseState\":\"responded_visible_message\",\"ledgerStatus\":\"responded\",\"visibleReplyMessageId\":\"d4065728-b244-4e53-a8cf-d33d7de62a6f\",\"visibleReplyCorrelation\":\"relayOfMessageId\",\"diagnostics\":[\"OpenCode app MCP is connected for message delivery.\",\"OpenCode prompt_async accepted after a turn-settled guard; response observation remains delegated to durable app-side ledger reconciliation.\"]}",
+        "peerDelivery={\"delivered\":true,\"accepted\":true,\"responsePending\":false,\"responseState\":\"responded_visible_message\",\"ledgerStatus\":\"responded\",\"visibleReplyMessageId\":\"37187280-1220-44da-a5d3-a3fdf812cc3a\",\"visibleReplyCorrelation\":\"relayOfMessageId\",\"diagnostics\":[\"OpenCode app MCP is connected for message delivery.\",\"OpenCode prompt_async accepted after a turn-settled guard; response observation remains delegated to durable app-side ledger reconciliation.\"]}"
+      ]
+    }
+  ]
+}