Update .eval_results/ngen4-official-benchmarks.yaml

.eval_results/ngen4-official-benchmarks.yaml

@@ -277,38 +277,4 @@
   date: '2026-04-05'
   source:
     url: https://tnsaai.com/models/ngen4
-    name: TNSA NGen-4 Evaluations
-
-- dataset:
-    id: TIGER-Lab/MMLU-Pro
-    task_id: mmlu_pro
-  value: 89.6
-  date: '2026-04-06'
-  source:
-    url: https://tnsaai.com/models/ngen4
-    name: TNSA NGen-4 Evaluations
-- dataset:
-    id: Idavidrein/gpqa
-    task_id: diamond
-  value: 90.1
-  date: '2026-04-06'
-  source:
-    url: https://tnsaai.com/models/ngen4
-    name: TNSA NGen-4 Evaluations
-- dataset:
-    id: SWE-bench/SWE-bench_Verified
-    task_id: swe_bench_%_resolved
-  value: 72.7
-  date: '2026-04-06'
-  source:
-    url: https://tnsaai.com/models/ngen4
-    name: TNSA NGen-4 Evaluations
-- dataset:
-    id: harborframework/terminal-bench-2.0
-    task_id: terminal_bench
-  value: 42.5
-  date: '2026-04-06'
-  source:
-    url: https://tnsaai.com/models/ngen4
-    name: TNSA NGen-4 Evaluations
-
+    name: TNSA NGen-4 Evaluations