Add LEXam-hard evaluation result

Adds this model's score on the [LEXam-hard](https://huggingface.co/datasets/joelniklaus/LEXam-hard) benchmark, the 518 LEXam open questions the strongest open models score lowest on.

The score is the pooled mean DeepSeek-R1-0528 judge grade (0-100) over those questions, recomputed from the per-sample outputs of the [SwissLegalEvals](https://huggingface.co/blog/joelniklaus/swiss-legal-evals) run (lighteval, LEXam paper prompts, one response per question, no tools). The raw outputs are in the public `joelniklaus/SwissLegalEvals` bucket; the recomputation is `reproduction/lexam_hard_results.py` in the dataset repository.

.eval_results/lexam-hard.yaml

@@ -0,0 +1,12 @@
+- dataset:
+    id: joelniklaus/LEXam-hard
+    task_id: lexam_hard
+    revision: ed6d99edf964592f1a1d34f52ca9158ceda0f7af
+  value: 30.81
+  date: '2026-07-27'
+  source:
+    url: https://huggingface.co/buckets/joelniklaus/SwissLegalEvals
+    name: SwissLegalEvals per-sample details (lighteval)
+    user: joelniklaus
+  notes: lighteval, LEXam paper prompts, one response per question, no tools; DeepSeek-R1-0528 judge;
+    pooled mean over the 518 questions, 0-100