Add Thinking/Non-Thinking variant notes
Browse files
.eval_results/openPangu-2.0-Flash.yaml
CHANGED
|
@@ -6,6 +6,7 @@
|
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 8 |
name: "openPangu-2.0-Flash model card"
|
|
|
|
| 9 |
|
| 10 |
- dataset:
|
| 11 |
id: MathArena/aime_2026
|
|
@@ -15,6 +16,7 @@
|
|
| 15 |
source:
|
| 16 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 17 |
name: "openPangu-2.0-Flash model card"
|
|
|
|
| 18 |
|
| 19 |
- dataset:
|
| 20 |
id: Idavidrein/gpqa
|
|
@@ -24,7 +26,7 @@
|
|
| 24 |
source:
|
| 25 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 26 |
name: "openPangu-2.0-Flash model card"
|
| 27 |
-
notes: "Avg@4"
|
| 28 |
|
| 29 |
- dataset:
|
| 30 |
id: Idavidrein/gpqa
|
|
@@ -34,7 +36,7 @@
|
|
| 34 |
source:
|
| 35 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 36 |
name: "openPangu-2.0-Flash model card"
|
| 37 |
-
notes: "Avg@4"
|
| 38 |
|
| 39 |
- dataset:
|
| 40 |
id: claw-eval/Claw-Eval
|
|
@@ -44,7 +46,7 @@
|
|
| 44 |
source:
|
| 45 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 46 |
name: "openPangu-2.0-Flash model card"
|
| 47 |
-
notes: "Pass^3"
|
| 48 |
|
| 49 |
- dataset:
|
| 50 |
id: claw-eval/Claw-Eval
|
|
@@ -54,7 +56,7 @@
|
|
| 54 |
source:
|
| 55 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 56 |
name: "openPangu-2.0-Flash model card"
|
| 57 |
-
notes: "Pass^3"
|
| 58 |
|
| 59 |
- dataset:
|
| 60 |
id: internlm/WildClawBench
|
|
@@ -64,7 +66,7 @@
|
|
| 64 |
source:
|
| 65 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 66 |
name: "openPangu-2.0-Flash model card"
|
| 67 |
-
notes: "Avg@3"
|
| 68 |
|
| 69 |
- dataset:
|
| 70 |
id: internlm/WildClawBench
|
|
@@ -74,7 +76,7 @@
|
|
| 74 |
source:
|
| 75 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 76 |
name: "openPangu-2.0-Flash model card"
|
| 77 |
-
notes: "Avg@3"
|
| 78 |
|
| 79 |
- dataset:
|
| 80 |
id: SWE-bench/SWE-bench_Verified
|
|
@@ -84,7 +86,7 @@
|
|
| 84 |
source:
|
| 85 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 86 |
name: "openPangu-2.0-Flash model card"
|
| 87 |
-
notes: "Avg@3"
|
| 88 |
|
| 89 |
- dataset:
|
| 90 |
id: SWE-bench/SWE-bench_Verified
|
|
@@ -94,4 +96,4 @@
|
|
| 94 |
source:
|
| 95 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 96 |
name: "openPangu-2.0-Flash model card"
|
| 97 |
-
notes: "Avg@3"
|
|
|
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 8 |
name: "openPangu-2.0-Flash model card"
|
| 9 |
+
notes: "Thinking"
|
| 10 |
|
| 11 |
- dataset:
|
| 12 |
id: MathArena/aime_2026
|
|
|
|
| 16 |
source:
|
| 17 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 18 |
name: "openPangu-2.0-Flash model card"
|
| 19 |
+
notes: "Non-Thinking"
|
| 20 |
|
| 21 |
- dataset:
|
| 22 |
id: Idavidrein/gpqa
|
|
|
|
| 26 |
source:
|
| 27 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 28 |
name: "openPangu-2.0-Flash model card"
|
| 29 |
+
notes: "Avg@4, Thinking"
|
| 30 |
|
| 31 |
- dataset:
|
| 32 |
id: Idavidrein/gpqa
|
|
|
|
| 36 |
source:
|
| 37 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 38 |
name: "openPangu-2.0-Flash model card"
|
| 39 |
+
notes: "Avg@4, Non-Thinking"
|
| 40 |
|
| 41 |
- dataset:
|
| 42 |
id: claw-eval/Claw-Eval
|
|
|
|
| 46 |
source:
|
| 47 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 48 |
name: "openPangu-2.0-Flash model card"
|
| 49 |
+
notes: "Pass^3, Thinking"
|
| 50 |
|
| 51 |
- dataset:
|
| 52 |
id: claw-eval/Claw-Eval
|
|
|
|
| 56 |
source:
|
| 57 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 58 |
name: "openPangu-2.0-Flash model card"
|
| 59 |
+
notes: "Pass^3, Non-Thinking"
|
| 60 |
|
| 61 |
- dataset:
|
| 62 |
id: internlm/WildClawBench
|
|
|
|
| 66 |
source:
|
| 67 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 68 |
name: "openPangu-2.0-Flash model card"
|
| 69 |
+
notes: "Avg@3, Thinking"
|
| 70 |
|
| 71 |
- dataset:
|
| 72 |
id: internlm/WildClawBench
|
|
|
|
| 76 |
source:
|
| 77 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 78 |
name: "openPangu-2.0-Flash model card"
|
| 79 |
+
notes: "Avg@3, Non-Thinking"
|
| 80 |
|
| 81 |
- dataset:
|
| 82 |
id: SWE-bench/SWE-bench_Verified
|
|
|
|
| 86 |
source:
|
| 87 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 88 |
name: "openPangu-2.0-Flash model card"
|
| 89 |
+
notes: "Avg@3, Thinking"
|
| 90 |
|
| 91 |
- dataset:
|
| 92 |
id: SWE-bench/SWE-bench_Verified
|
|
|
|
| 96 |
source:
|
| 97 |
url: https://huggingface.co/openpangu/openPangu-2.0-Flash
|
| 98 |
name: "openPangu-2.0-Flash model card"
|
| 99 |
+
notes: "Avg@3, Non-Thinking"
|