SaylorTwift HF Staff commited on
Commit
ef26beb
·
verified ·
1 Parent(s): 5b78fc7

Add evaluation results

Browse files
.eval_results/openPangu-2.0-Flash.yaml ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: MathArena/aime_2026
3
+ task_id: MathArena/aime_2026
4
+ value: 93.3
5
+ date: "2026-07-01"
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
12
+ task_id: MathArena/aime_2026
13
+ value: 86.5
14
+ date: "2026-07-01"
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
21
+ task_id: diamond
22
+ value: 83.7
23
+ date: "2026-07-01"
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
31
+ task_id: diamond
32
+ value: 79.8
33
+ date: "2026-07-01"
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
41
+ task_id: general
42
+ value: 57.7
43
+ date: "2026-07-01"
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
51
+ task_id: general
52
+ value: 58.2
53
+ date: "2026-07-01"
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
61
+ task_id: overall
62
+ value: 41.5
63
+ date: "2026-07-01"
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
71
+ task_id: overall
72
+ value: 35.0
73
+ date: "2026-07-01"
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
81
+ task_id: swe_bench_%_resolved
82
+ value: 63.1
83
+ date: "2026-07-01"
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
91
+ task_id: swe_bench_%_resolved
92
+ value: 57.6
93
+ date: "2026-07-01"
94
+ source:
95
+ url: https://huggingface.co/openpangu/openPangu-2.0-Flash
96
+ name: "openPangu-2.0-Flash model card"
97
+ notes: "Avg@3"