Add evaluation results from Step 3.5 Flash paper - HLE (text only): 23.1 - GPQA Diamond: 83.5 - MMLU-Pro: 84.4 - SWE-Bench Verified: 74.4% - Terminal-Bench 2.0: 51.0% Source: https://arxiv.org/abs/2602.10604 (Table 5, Vanilla inference)

.eval_results/gpqa_diamond.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 83.5
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/hle.yaml

@@ -0,0 +1,10 @@
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 23.1
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift
+  notes: "Text Only"

.eval_results/mmlu_pro.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 84.4
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/swe_bench_verified.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 74.4
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift

.eval_results/terminal_bench_2.yaml

@@ -0,0 +1,9 @@
+- dataset:
+    id: harborframework/terminal-bench-2.0
+    task_id: terminalbench_2
+  value: 51.0
+  date: '2026-02-11'
+  source:
+    url: https://arxiv.org/abs/2602.10604
+    name: Step 3.5 Flash Paper
+    user: SaylorTwift