diff --git a/evalharness/model/runner.py b/evalharness/model/runner.py
index a720fc1..7ce7752 100644
--- a/evalharness/model/runner.py
+++ b/evalharness/model/runner.py
@@ -360,8 +360,6 @@ async def generate_predictions(
         return {'raw': text, 'usage': out.usage.model_dump()}
 
     work = _apply_limits(samples, limit, limit_per_task, shuffle=not no_shuffle)
-    if status_callback:
-        status_callback(f'preparing {len(work)} evaluation samples')
     # checkpointing: restore completed samples, generate only the rest
     ckpt_store = None
     if checkpoint:
@@ -398,15 +396,15 @@ async def generate_predictions(
             preds_by_key[k] = restored[k]
         else:
             pending.append((i, s))
-    if ckpt_store is not None and restored:
-        line = (f'checkpoint restored {len(restored)} predictions '
-                f'({len(pending)} to generate) -> {ckpt_store.path}')
-        if status_callback:
-            status_callback(line)
+    if status_callback:
+        if restored:
+            status_callback(f'{len(work)} samples · checkpoint {len(restored)}/{len(work)} '
+                            f'restored, {len(pending)} to generate')
         else:
-            print(f'checkpoint: {line}', flush=True)
-        if status_callback:
-            status_callback(f'checkpoint restored: {len(restored)} ready, {len(pending)} pending')
+            status_callback(f'{len(work)} samples')
+    elif restored:
+        print(f'checkpoint: restored {len(restored)} predictions '
+              f'({len(pending)} to generate) -> {ckpt_store.path}', flush=True)
 
     if progress_reporter is not None:
         progress_reporter.reset_samples(len(work), dataset_name, completed=len(restored))
@@ -435,14 +433,17 @@ async def generate_predictions(
 
     try:
         if status_callback:
-            status_callback(f'generating model responses: {len(pending)} pending')
+            if pending:
+                status_callback(f'generating {len(pending)} responses')
+            else:
+                status_callback('generation skipped · checkpoint complete')
         fresh = await asyncio.gather(*(run_one((i, s)) for i, s in pending))
         for i, pred in fresh:
             preds_by_key[keys[i]] = pred
         preds = [preds_by_key[k] for k in keys]
         usages = [p.get('usage', {}) for p in preds]
-        if status_callback:
-            status_callback(f'generation complete: {len(preds)} responses')
+        if status_callback and pending:
+            status_callback(f'generation complete · {len(preds)} responses')
         return preds, usages, total_usage
     finally:
         # reporter lifecycle belongs to the CALLER (CLI reuses one reporter
@@ -730,7 +731,10 @@ async def run_eval(
     report.model = model_spec
     report.dataset = name
     if status_callback:
-        status_callback('scoring complete')
+        _m = next(((k, v) for k, v in report.metrics.items()
+                   if k != 'extraction_failure_rate'), None)
+        status_callback(f'scoring complete · {_m[0]} {_m[1] * 100:.1f}%'
+                        if _m else 'scoring complete')
     # performance profile: pool success rate + latency/ttft percentiles
     try:
         from .aggregator import get_aggregator