Add Qwen3.6 validation and benchmark coverage

tools/bench/report.py

@@ -32,7 +32,11 @@ def _speed_table(rows: list[dict[str, Any]]) -> str:
 
     by = {(r["system"], r["scenario"]): r for r in rows}
     out = []
-    out.append("| scenario | metric | " + " | ".join(systems) + " | speedup (xserv ÷ llama.cpp) |")
+    out.append(
+        "| scenario | metric | "
+        + " | ".join(systems)
+        + " | xserv relative performance (higher is better) |"
+    )
     out.append("|---|---|" + "|".join(["---"] * (len(systems) + 1)) + "|")
 
     metrics = [
@@ -68,13 +72,13 @@ def _quality_table(rows: list[dict[str, Any]]) -> str:
     for r in rows:
         by_task.setdefault(r["task"], []).append(r)
     out: list[str] = []
-    out.append("| task | system | n | correct | accuracy | mean tokens | TTFT (ms) | TPOT (ms/tok) | wall (s) |")
-    out.append("|---|---|---|---|---|---|---|---|---|")
+    out.append("| task | system | n | correct | accuracy | length | mean tokens | TTFT (ms) | TPOT (ms/tok) | wall (s) |")
+    out.append("|---|---|---|---|---|---|---|---|---|---|")
     for task, task_rows in by_task.items():
         for r in task_rows:
             out.append(
                 f"| {task} | {r['system']} | {r['n_total']} | {r['n_correct']} | "
-                f"{r['accuracy'] * 100:.1f}% | {r['mean_completion_tokens']:.0f} | "
+                f"{r['accuracy'] * 100:.1f}% | {r['n_length']} | {r['mean_completion_tokens']:.0f} | "
                 f"{_fmt(r['mean_ttft_ms'])} | {_fmt(r['mean_tpot_ms'], 2)} | {r['wall_s']:.1f} |"
             )
     return "\n".join(out) + "\n"