Add evaluation results for Ling-3.0-flash (#3)

- Add evaluation results for Ling-3.0-flash (3f6f7dcd47a69b82d3c1964c1d9b11e77a635d8a)
- Match main.py evaluation result format (a8a8cb4b8710aa06a4465d94afa8151c36069827)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

.eval_results/aime_2026.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: MathArena/aime_2026
+    task_id: MathArena/aime_2026
+  value: 93.2
+  source:
+    url: https://huggingface.co/inclusionAI/Ling-3.0-flash
+    name: Model Card

.eval_results/hle.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 22.7
+  source:
+    url: https://huggingface.co/inclusionAI/Ling-3.0-flash
+    name: Model Card

.eval_results/hmmt_feb_2026.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: MathArena/hmmt_feb_2026
+    task_id: MathArena/hmmt_feb_2026
+  value: 87.0
+  source:
+    url: https://huggingface.co/inclusionAI/Ling-3.0-flash
+    name: Model Card

.eval_results/swe-bench_multilingual.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: SWE-bench/SWE-bench_Multilingual
+    task_id: swe_bench_multilingual_%_resolved
+  value: 72.4
+  source:
+    url: https://huggingface.co/inclusionAI/Ling-3.0-flash
+    name: Model Card

.eval_results/swe-bench_pro.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: ScaleAI/SWE-bench_Pro
+    task_id: SWE_Bench_Pro
+  value: 56.6
+  source:
+    url: https://huggingface.co/inclusionAI/Ling-3.0-flash
+    name: Model Card