Add evaluation results: HLE, GPQA Diamond, SWE-bench Verified, Terminal-Bench 2.0
Browse files
.eval_results/gpqa.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: Idavidrein/gpqa
|
| 3 |
+
task_id: diamond
|
| 4 |
+
value: 87.2
|
| 5 |
+
date: '2026-04-14'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/tencent/Hy3-preview
|
| 8 |
+
name: Model Card
|
| 9 |
+
|
.eval_results/hle.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: cais/hle
|
| 3 |
+
task_id: hle
|
| 4 |
+
value: 30.0
|
| 5 |
+
date: '2026-04-14'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/tencent/Hy3-preview
|
| 8 |
+
name: Model Card
|
| 9 |
+
notes: "Text-only"
|
.eval_results/swe_bench_verified.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: SWE-bench/SWE-bench_Verified
|
| 3 |
+
task_id: swe_bench_%_resolved
|
| 4 |
+
value: 74.4
|
| 5 |
+
date: '2026-04-14'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/tencent/Hy3-preview
|
| 8 |
+
name: Model Card
|
| 9 |
+
|
.eval_results/terminal_bench.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: harborframework/terminal-bench-2.0
|
| 3 |
+
task_id: terminalbench_2
|
| 4 |
+
value: 54.4
|
| 5 |
+
date: '2026-04-14'
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/tencent/Hy3-preview
|
| 8 |
+
name: Model Card
|
| 9 |
+
|